© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113430
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    References to DOM element access (document.getElementById and accessing element.style/visibility) and visibility-checking code.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oming
    -0.08
    IXEL
    -0.07
    看了
    -0.07
    rafted
    -0.07
    אמת
    -0.06
    .cond
    -0.06
    .AdapterView
    -0.06
     Sinatra
    -0.06
    昣
    -0.06
    iap
    -0.06
    POSITIVE LOGITS
     antig
    0.07
     locking
    0.07
    คว
    0.07
    的存在
    0.06
     Lower
    0.06
    _cid
    0.06
    安全管理
    0.06
     Hải
    0.06
     <?=$
    0.06
    ✙
    0.06
    Activations Density 0.179%

    No Known Activations