© 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. 43247
    Prev
    Next
    INDEX
    Explanations

    code function names

    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
    urf
    -0.06
    åĸ³
    -0.06
    prises
    -0.06
    æī¿åĬŀåįķä½į
    -0.06
    说çĿĢ
    -0.06
    èĮ¬
    -0.06
    çĽijèĢĥ
    -0.06
    elect
    -0.06
    åĬ²åĦ¿
    -0.06
    prise
    -0.06
    POSITIVE LOGITS
    scheid
    0.08
     tame
    0.08
     suppor
    0.07
    efeld
    0.07
    å¿ħçľĭ
    0.07
    deque
    0.07
    intl
    0.07
    à§įন
    0.07
    @[
    0.07
     assms
    0.07
    Activations Density 0.006%

    No Known Activations