© 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. 32423
    Prev
    Next
    INDEX
    Explanations

    check or correct values

    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
    æŃ£å¼ıå¼Ģå§ĭ
    -0.07
    -
    -0.07
    '
    -0.07
    ç±»çŃī
    -0.06
    详ç»Ĩä»ĭç»į
    -0.06
    ÑĢад
    -0.06
    +
    -0.06
    /her
    -0.06
    datal
    -0.06
    å½ĵ家
    -0.06
    POSITIVE LOGITS
    ing
    0.15
    ÏĤ
    0.11
    ingen
    0.09
    ingar
    0.08
    Ø©
    0.08
    sWith
    0.08
    ingt
    0.08
    и
    0.08
    ingss
    0.08
    edList
    0.07
    Activations Density 0.001%

    No Known Activations