© 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. 19-RESID-POST-AA
    11. 37504
    Prev
    Next
    INDEX
    Explanations

    Code and programming instructions

    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
    Negative Logits
    ặp
    -0.08
     noticias
    -0.07
    자의
    -0.07
     ambiguous
    -0.07
     נש
    -0.07
     José
    -0.07
    绀
    -0.07
    为之
    -0.06
    גבר
    -0.06
    蕈
    -0.06
    POSITIVE LOGITS
    .domain
    0.07
    getConnection
    0.06
    Gar
    0.06
    .While
    0.06
     Sort
    0.06
     methodName
    0.06
    Ҁ
    0.06
    //------------------------------------------------
    0.06
    天涯
    0.06
    调度
    0.06
    Activations Density 0.024%

    No Known Activations