© 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. 30300
    Prev
    Next
    INDEX
    Explanations

    aforementioned or above

    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
    éĻ¢éĩĮ
    -0.08
    èĻı
    -0.08
    lom
    -0.07
     Viola
    -0.07
    .routes
    -0.06
    sec
    -0.06
    edig
    -0.06
    èį£
    -0.06
    oter
    -0.06
    ryn
    -0.06
    POSITIVE LOGITS
     tadi
    0.08
    çºĮ
    0.08
    åīįè¿°
    0.07
    utan
    0.07
    ä¸Ĭè¿°ä½ľåĵģ
    0.07
    .average
    0.07
    _ABORT
    0.07
    åĵ¼
    0.07
    ouvert
    0.07
     matem
    0.07
    Activations Density 0.110%

    No Known Activations