© 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. 62102
    Prev
    Next
    INDEX
    Explanations

    user dom

    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
     perpet
    -0.08
    alus
    -0.08
     Sin
    -0.06
     trag
    -0.06
    /sample
    -0.06
    IBUT
    -0.06
     lim
    -0.06
     withdraw
    -0.06
     Hoh
    -0.06
    _IE
    -0.05
    POSITIVE LOGITS
     NotImplemented
    0.09
    ehme
    0.08
    äºijå³°
    0.08
    terior
    0.08
    (([
    0.08
    åĩĨ
    0.08
    ciso
    0.08
    =""></
    0.07
     Scalar
    0.07
    indent
    0.07
    Activations Density 0.001%

    No Known Activations