© 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. 14370
    Prev
    Next
    INDEX
    Explanations

    religious texts

    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
     nulla
    -0.07
    Texture
    -0.07
    缌
    -0.07
     Manhattan
    -0.07
     olu
    -0.07
    孤独
    -0.07
     imagem
    -0.07
    là
    -0.07
    مشاهدة
    -0.07
     QString
    -0.07
    POSITIVE LOGITS
    В
    0.07
    订阅
    0.07
     '\'
    0.06
     {}
↵
↵
    0.06
    ionage
    0.06
    F
    0.06
    🅅
    0.06
    YPD
    0.06
    ('@
    0.06
    rew
    0.06
    Activations Density 0.013%

    No Known Activations