© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80268
    Prev
    Next
    INDEX
    Explanations

    .

    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
    .Socket
    -0.08
    Buscar
    -0.07
     Scope
    -0.07
    grese
    -0.06
     enctype
    -0.06
     Latest
    -0.06
    <body
    -0.06
    说过
    -0.06
    宝贵
    -0.06
    Warning
    -0.06
    POSITIVE LOGITS
    ycling
    0.08
    usement
    0.07
    �
    0.07
     rubbish
    0.06
            
↵
    0.06
     ,↵
    0.06
    _RGBA
    0.06
     hyster
    0.06
    aternion
    0.06
     لكن
    0.06
    Activations Density 0.128%

    No Known Activations