© 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. 113081
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    平均水平
    -0.07
     usleep
    -0.07
    理解和
    -0.07
    thinkable
    -0.07
    仙女
    -0.07
    .VisualStudio
    -0.07
    scoped
    -0.07
    人群
    -0.07
    IRC
    -0.07
    _CHARS
    -0.07
    POSITIVE LOGITS
     exposes
    0.07
     reveal
    0.06
    >Name
    0.06
     signifies
    0.06
    ⓘ
    0.06
    -off
    0.06
    蓿
    0.06
     (-
    0.06
    然後
    0.06
    'r
    0.06
    Activations Density 0.001%

    No Known Activations