© 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. 15-RESID-POST-AA
    11. 30314
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    オリジナル
    -0.07
    英才
    -0.07
     Digital
    -0.07
     зарегистри
    -0.07
    伴随着
    -0.06
     calf
    -0.06
    _malloc
    -0.06
    媽媽
    -0.06
     Omar
    -0.06
     Account
    -0.06
    POSITIVE LOGITS
    八
    0.08
     repairs
    0.07
    ture
    0.07
    ⊙
    0.07
    reject
    0.07
    치
    0.07
    #import
    0.06
    uję
    0.06
     её
    0.06
    UED
    0.06
    Activations Density 0.072%

    No Known Activations