© 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. 32125
    Prev
    Next
    INDEX
    Explanations

    proportional hazards, mixture model

    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
    วà¸Ļ
    -0.08
     забо
    -0.08
     Vert
    -0.07
     fiber
    -0.07
    صب
    -0.07
     Fiber
    -0.07
    olt
    -0.07
    icolo
    -0.07
    piring
    -0.07
    å¼±çĶµ
    -0.07
    POSITIVE LOGITS
     pooled
    0.09
    .shared
    0.09
    /shared
    0.09
    åIJĪ并
    0.09
     pooling
    0.08
    èģĶåIJĪ
    0.08
    èģ¯åIJĪ
    0.08
     shared
    0.08
    shared
    0.07
     ÑģÑĤоÑĢон
    0.07
    Activations Density 0.001%

    No Known Activations