© 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. 19-RESID-POST-AA
    11. 70776
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CONSTANTS
    -0.07
    福音
    -0.07
    Um
    -0.07
     sermon
    -0.07
     unpopular
    -0.06
    ]){
↵
    -0.06
    IMUM
    -0.06
     ض
    -0.06
    .Read
    -0.06
     cookies
    -0.06
    POSITIVE LOGITS
    ģ
    0.07
    坚持不懈
    0.07
     Bắc
    0.07
    归属于
    0.07
    .setPrototypeOf
    0.07
    ateway
    0.07
    砫
    0.07
     Tactics
    0.07
     MACHINE
    0.07
     ấy
    0.07
    Activations Density 0.084%

    No Known Activations