© 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. 126848
    Prev
    Next
    INDEX
    Explanations

    ออ

    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
     quanto
    -0.07
    艋
    -0.06
     adım
    -0.06
     quel
    -0.06
     verifies
    -0.06
     quelle
    -0.06
    颡
    -0.06
    恼
    -0.06
     mano
    -0.06
    umno
    -0.06
    POSITIVE LOGITS
    /Framework
    0.07
    "*
    0.07
     intoxic
    0.07
    大湾区
    0.07
    /Open
    0.07
     Hollywood
    0.07
     fantastic
    0.07
     unserialize
    0.07
     רוצים
    0.07
    中国经济
    0.06
    Activations Density 0.014%

    No Known Activations