© 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. 44109
    Prev
    Next
    INDEX
    Explanations

    actions and operations

    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
    sWith
    -0.13
    swith
    -0.11
    spath
    -0.10
    sson
    -0.09
    they
    -0.09
    less
    -0.09
    ä¸Ģ件äºĭæĥħ
    -0.09
    ish
    -0.08
    ä¸Ģç±»
    -0.08
    /disable
    -0.08
    POSITIVE LOGITS
    heets
    0.13
    nya
    0.12
    cales
    0.12
    pring
    0.11
    chool
    0.11
    ervices
    0.11
    creens
    0.11
    ä¼ĹæīĢåij¨çŁ¥
    0.11
    uffix
    0.11
    ysteem
    0.11
    Activations Density 0.848%

    No Known Activations