© 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. 41742
    Prev
    Next
    INDEX
    Explanations

    blog post

    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
    ä¸įä½Ĩ
    -0.07
    è®°
    -0.07
    ahan
    -0.06
    /validation
    -0.06
     Kit
    -0.06
     validating
    -0.06
    转头
    -0.06
    订éĺħä¸ĵæłı
    -0.06
    venta
    -0.06
    æŀĦ
    -0.06
    POSITIVE LOGITS
    .exports
    0.09
    ouser
    0.08
    _partial
    0.08
    åŃĺæľī
    0.08
    áĥ£áĥł
    0.07
    WithType
    0.07
     clearer
    0.07
    西åħ°
    0.07
    çĶ¨æĪ·ä½¿çĶ¨
    0.07
    Äĥt
    0.07
    Activations Density 0.001%

    No Known Activations