© 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. 121248
    Prev
    Next
    INDEX
    Explanations

    prices

    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
    Limited
    -0.09
    Dragging
    -0.08
    بني
    -0.07
    *******↵
    -0.07
     werden
    -0.07
    经济效益
    -0.07
     contin
    -0.07
     Yun
    -0.07
    退役军人
    -0.07
    ומות
    -0.07
    POSITIVE LOGITS
    出租
    0.08
     impactful
    0.07
     specialist
    0.06
    æk
    0.06
    HAM
    0.06
     surf
    0.06
    ʔ
    0.06
    ,h
    0.06
     decrement
    0.06
    loi
    0.06
    Activations Density 0.007%

    No Known Activations