© 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. 65240
    Prev
    Next
    INDEX
    Explanations

    native or local code/functionality

    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
    musik
    -0.09
    θά
    -0.09
    Gram
    -0.08
    (edit
    -0.08
    tida
    -0.08
    涨åĬ¿
    -0.08
    olgen
    -0.08
    boh
    -0.08
    .erb
    -0.08
    odon
    -0.08
    POSITIVE LOGITS
     native
    0.11
    _native
    0.10
    Native
    0.10
    native
    0.10
     Native
    0.08
    /native
    0.08
    local
    0.07
    _NATIVE
    0.07
    åĽłåľ°åĪ¶å®ľ
    0.07
     local
    0.07
    Activations Density 0.262%

    No Known Activations