© 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. 11-RESID-POST-AA
    11. 72135
    Prev
    Next
    INDEX
    Explanations

    of

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    \Base
    -0.08
     llen
    -0.07
    KC
    -0.07
    Tank
    -0.07
     zo
    -0.07
    瘆
    -0.06
    htmlspecialchars
    -0.06
    歩
    -0.06
     Bernard
    -0.06
     đứ
    -0.06
    POSITIVE LOGITS
     affiliates
    0.08
    回顾
    0.07
    这一切
    0.07
     linked
    0.07
    .lift
    0.07
    (contract
    0.07
     règle
    0.07
    东盟
    0.07
    เอกสาร
    0.06
    軟體
    0.06
    Activations Density 0.001%

    No Known Activations