© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62161
    Prev
    Next
    INDEX
    Explanations

    ascending and descending movement

    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
    ìĤ¬íķŃ
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    chy
    -0.08
    umente
    -0.08
    argar
    -0.07
    หมาย
    -0.07
    å°Ķæĸ¯
    -0.07
    жание
    -0.07
    ìĻ¸
    -0.07
    raries
    -0.07
    POSITIVE LOGITS
    ertainment
    0.09
    è¿ĩç¨ĭä¸Ń
    0.08
    agak
    0.07
    éĢĶä¸Ńãģ§
    0.07
    atoire
    0.07
    atory
    0.07
    راط
    0.07
    áĥĿáĥij
    0.07
    worthy
    0.07
    è¿ĩç¨ĭçļĦ
    0.07
    Activations Density 0.024%

    No Known Activations