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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 129689
    Prev
    Next
    INDEX
    Explanations

    counting in programming

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asic
    -0.06
    穩
    -0.06
     Ron
    -0.06
     Walnut
    -0.06
     bán
    -0.06
     -------------
    -0.06
     Rat
    -0.06
    审核
    -0.06
    Ẵ
    -0.06
     rq
    -0.06
    POSITIVE LOGITS
    (enemy
    0.08
    .aspx
    0.08
    🔁
    0.07
    .har
    0.07
    unicorn
    0.07
     divisions
    0.07
    iferay
    0.07
    곸
    0.07
     accountability
    0.07
     effected
    0.06
    Activations Density 0.194%

    No Known Activations