© 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. 19-RESID-POST-AA
    11. 70955
    Prev
    Next
    INDEX
    Explanations

    Expertise and Understanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doing
    -0.08
     gchar
    -0.07
    _DRV
    -0.07
    .dropout
    -0.07
    _Order
    -0.07
    党组书记
    -0.07
    Toyota
    -0.07
     Longer
    -0.07
    ואב
    -0.07
    _colors
    -0.07
    POSITIVE LOGITS
    Blocked
    0.07
     warranted
    0.06
    bonus
    0.06
    zones
    0.06
    lines
    0.06
    '}
    0.06
    LAND
    0.06
    الياب
    0.06
    分流
    0.06
    (block
    0.06
    Activations Density 0.020%

    No Known Activations