© 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. 3490
    Prev
    Next
    INDEX
    Explanations

    expand mathematical expressions

    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
    pst
    -0.08
    quat
    -0.07
    RenderingContext
    -0.07
    getattr
    -0.07
    æĸ°æľĪ
    -0.07
    RAIN
    -0.07
    ä¸ĵåįĸåºĹ
    -0.07
    ç¥ŀå±±
    -0.07
    toDouble
    -0.07
    .deep
    -0.07
    POSITIVE LOGITS
    å°Ĩè¿ĻäºĽ
    0.08
    ä½łå°Ĩ
    0.08
    å¡ŀ
    0.07
    å°Ĩåħ¶
    0.07
     Expanded
    0.07
    heiros
    0.07
    .ordinal
    0.07
    ibern
    0.07
     hale
    0.07
    yr
    0.06
    Activations Density 0.005%

    No Known Activations