© 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. 9477
    Prev
    Next
    INDEX
    Explanations

    cancer prognosis, maturity stages, glass panel

    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
    æĭĵ
    -0.08
    èĢħä¹Ł
    -0.08
    æ³ķæĺ¯
    -0.07
    _SOFT
    -0.06
     Levine
    -0.06
    æķ¢
    -0.06
     Betr
    -0.06
    æ³ķ
    -0.06
    jian
    -0.06
     Took
    -0.06
    POSITIVE LOGITS
    INAS
    0.08
    fq
    0.07
    blas
    0.07
    лаÑģ
    0.07
    egos
    0.07
    olean
    0.07
    istri
    0.07
    हार
    0.07
    ħĮ
    0.07
    _enqueue
    0.07
    Activations Density 0.284%

    No Known Activations