© 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. 64076
    Prev
    Next
    INDEX
    Explanations

    status and text fields

    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
    åĨīåĨī
    -0.08
    ä¼Ĭæĸ¯
    -0.07
    NST
    -0.07
    biet
    -0.07
    nika
    -0.07
    nof
    -0.07
    æıIJéĨĴèĩªå·±
    -0.07
    볼
    -0.07
    Dimensions
    -0.07
    itore
    -0.07
    POSITIVE LOGITS
    estatus
    0.08
    án
    0.08
    oub
    0.07
    getStatus
    0.06
    ijkstra
    0.06
    åįĬå²Ľ
    0.06
    _statuses
    0.06
     distances
    0.06
    dating
    0.06
    赫å°Ķ
    0.06
    Activations Density 0.001%

    No Known Activations