© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29982
    Prev
    Next
    INDEX
    Explanations

    velocity

    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
    edly
    -0.08
    isle
    -0.07
    side
    -0.07
    istry
    -0.07
    vention
    -0.07
    ald
    -0.07
    æ¡Įä¸Ĭ
    -0.06
    abouts
    -0.06
    ethyst
    -0.06
    eness
    -0.06
    POSITIVE LOGITS
    ocities
    0.13
    byname
    0.09
    geber
    0.09
    ipped
    0.09
    erno
    0.09
    osamente
    0.09
    anguard
    0.09
    ancier
    0.08
    IRTUAL
    0.08
    acements
    0.08
    Activations Density 0.005%

    No Known Activations