© 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. 41947
    Prev
    Next
    INDEX
    Explanations

    `.init` or `init` function calls

    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
    elp
    -0.06
    ptom
    -0.06
    pent
    -0.06
    atus
    -0.06
    $sub
    -0.06
    CKER
    -0.06
    adlo
    -0.06
    aque
    -0.06
     Staples
    -0.06
    æĵį
    -0.06
    POSITIVE LOGITS
     sexi
    0.07
    лан
    0.07
    hô
    0.07
    Ñħова
    0.07
    ãģĹãģ¶
    0.07
    horn
    0.07
    åĬ¹
    0.07
    éĽĨåĽ¢èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    jen
    0.07
    Hints
    0.07
    Activations Density 0.408%

    No Known Activations