© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64980
    Prev
    Next
    INDEX
    Explanations

    contribution

    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
    ursos
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    大纲
    -0.08
    axy
    -0.07
    izzi
    -0.07
    .lot
    -0.07
    @a
    -0.07
    éķ¿åģĩ
    -0.07
    oya
    -0.07
    kana
    -0.07
    POSITIVE LOGITS
     contributions
    0.14
    è´¡çĮ®
    0.12
     Contribution
    0.11
     contribution
    0.11
    çļĦè´¡çĮ®
    0.11
     Contributions
    0.11
     contributes
    0.10
    contrib
    0.10
     contribute
    0.10
    -contrib
    0.10
    Activations Density 0.002%

    No Known Activations