© 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. 33003
    Prev
    Next
    INDEX
    Explanations

    locking pin or press button

    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
    å¨
    -0.06
    èĤĨ
    -0.06
     tre
    -0.06
    aniem
    -0.06
    .Property
    -0.06
    _cast
    -0.06
    大åĬŁ
    -0.06
    _links
    -0.06
    åĺ²
    -0.06
    usco
    -0.06
    POSITIVE LOGITS
    ullet
    0.08
    çĤ¹çĤ¹æ»´æ»´
    0.07
    åı¹äºĨä¸Ģåı£æ°Ķ
    0.07
    etype
    0.07
    ấy
    0.07
    à¸ļวà¸Ļà¸ģาร
    0.07
    èľĴ
    0.07
    ÑĦÑĢо
    0.07
    chÄĻ
    0.07
    ÐĿЯ
    0.07
    Activations Density 0.017%

    No Known Activations