© 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. 20313
    Prev
    Next
    INDEX
    Explanations

    advance

    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
    yss
    -0.07
    è§ģçĬ¶
    -0.07
    ä¹Ķ
    -0.07
    _BOUNDS
    -0.07
    çłģ
    -0.07
    ä¸Ĭåĵģ
    -0.07
    stuhl
    -0.07
    纳德
    -0.07
    .Compiler
    -0.07
    umerator
    -0.07
    POSITIVE LOGITS
    niu
    0.07
    menn
    0.07
    skem
    0.07
    æľī家
    0.07
    èĻķçļĦ
    0.07
    ined
    0.07
    tii
    0.07
    APPED
    0.06
    lein
    0.06
    åĽ½æĹĹä¸ĭ
    0.06
    Activations Density 0.014%

    No Known Activations