© 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. 8494
    Prev
    Next
    INDEX
    Explanations

    code snippets with .js or code constructs

    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
    okok
    -0.10
    PropertyDescriptor
    -0.09
    EmptyEntries
    -0.09
    æłĩè¯Ĩçłģ
    -0.08
    ReturnValue
    -0.08
    RequestMethod
    -0.08
    è·¯åĮĹ
    -0.08
    _icall
    -0.08
    .nih
    -0.08
    _redirected
    -0.08
    POSITIVE LOGITS
    /
    0.09
    +
    0.08
    <
    0.08
    _mode
    0.07
    -
    0.07
    ette
    0.07
    d
    0.07
     FIXME
    0.07
    e
    0.07
    ->
    0.07
    Activations Density 0.581%

    No Known Activations