© 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. 39675
    Prev
    Next
    INDEX
    Explanations

    PSA recurrence

    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
    à¸ĺà¸ĩ
    -0.08
    ellerie
    -0.08
    Intern
    -0.07
    ResponseType
    -0.07
    éĻ°
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    Ī¬
    -0.07
    _Space
    -0.07
    intern
    -0.07
    ³
    -0.07
    POSITIVE LOGITS
    åı±
    0.07
    ä¾
    0.07
     d
    0.07
    imea
    0.06
    aza
    0.06
    blia
    0.06
    kerne
    0.06
     unif
    0.06
     procur
    0.06
    èĬ¯
    0.06
    Activations Density 0.123%

    No Known Activations