© 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. 120360
    Prev
    Next
    INDEX
    Explanations

    ixed

    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
    <message
    -0.07
     Cock
    -0.07
     lucky
    -0.07
     Comedy
    -0.07
     dense
    -0.07
     flask
    -0.07
    olk
    -0.07
    Checked
    -0.07
    ,max
    -0.07
    重点关注
    -0.06
    POSITIVE LOGITS
     الخ
    0.07
     Mariners
    0.07
        
↵    
↵
    0.07
    vs
    0.07
    .GetLength
    0.07
    交接
    0.07
    interpre
    0.07
    עבוד
    0.07
    XXXXXXXX
    0.06
    损失
    0.06
    Activations Density 0.000%

    No Known Activations