© 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. 78770
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Sponsored
    -0.09
     spokesman
    -0.08
    Consult
    -0.08
    Spot
    -0.07
    	my
    -0.07
    <U
    -0.07
    _sup
    -0.07
    Tween
    -0.07
    _summary
    -0.07
     mystery
    -0.07
    POSITIVE LOGITS
    ##↵↵
    0.07
    蜿
    0.07
    ﮨ
    0.06
    市场化
    0.06
    롸
    0.06
    돗
    0.06
    𝐢
    0.06
    greSQL
    0.06
     Econom
    0.06
    港
    0.06
    Activations Density 0.001%

    No Known Activations