© 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. 18957
    Prev
    Next
    INDEX
    Explanations

    Keywords

    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
    çĸ
    -0.07
    ])->
    -0.07
    ())->
    -0.07
    abouts
    -0.07
    wski
    -0.07
    teres
    -0.07
    .gc
    -0.07
    ¯
    -0.07
    anches
    -0.06
    .cwd
    -0.06
    POSITIVE LOGITS
    edBy
    0.08
    Constructor
    0.06
    estu
    0.06
     enten
    0.06
    once
    0.06
    ä¸Ĭçľĭ
    0.06
    Ctl
    0.06
    acken
    0.06
    ì½ľ
    0.06
    yna
    0.06
    Activations Density 0.001%

    No Known Activations