© 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. 25289
    Prev
    Next
    INDEX
    Explanations

    disabled states

    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
    fer
    -0.08
    ONGL
    -0.07
    ä¸įåİĮ
    -0.07
    èĤºèħij
    -0.07
    ä¼ı
    -0.07
    ester
    -0.07
    Retention
    -0.07
    ÙĪتر
    -0.07
    els
    -0.07
    chw
    -0.07
    POSITIVE LOGITS
     disables
    0.10
     disable
    0.09
    disable
    0.09
    ç¦ģ
    0.09
    _disable
    0.08
    ç¦ģçĶ¨
    0.08
    immune
    0.08
    /disable
    0.08
     disabled
    0.08
     prohibits
    0.08
    Activations Density 0.089%

    No Known Activations