© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51900
    Prev
    Next
    INDEX
    Explanations

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .CreateCommand
    -0.09
    ®
    -0.08
    advert
    -0.08
    åĮħè£ħ设计
    -0.08
    heed
    -0.08
    çĶļèĩ³æľīäºĽ
    -0.07
    .IsNullOr
    -0.07
    authent
    -0.07
    Unnamed
    -0.07
    ujan
    -0.07
    POSITIVE LOGITS
    imit
    0.08
    ...
    0.07
    çŃĸ
    0.07
    tern
    0.07
    ..."
    0.06
    åģıåģı
    0.06
    culo
    0.06
    人å¿ĥ
    0.06
    éĤ¦
    0.06
     Giac
    0.06
    Activations Density 0.070%

    No Known Activations