© 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. 21741
    Prev
    Next
    INDEX
    Explanations

    use foruse in

    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
    å®īæİĴ好
    -0.08
     cocci
    -0.07
    abend
    -0.07
    éĢļè¿ĩ对
    -0.07
    åİī
    -0.07
    à·Ĵනà·Ĭ
    -0.07
    ffit
    -0.06
    ipline
    -0.06
     concerted
    -0.06
    drm
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºåħ¶
    0.13
    åĽłä¸ºå®ĥ
    0.12
    åĽłä¸ºè¿Ļ个
    0.11
    åĽłä¸ºå®ĥ们
    0.11
    çĶ¨ä½ľ
    0.10
    åĽłä¸ºä»ĸ们
    0.10
    åħħå½ĵ
    0.09
    ä»£æĽ¿
    0.09
    æĽ¿ä»£
    0.09
    æĽ¿ä»£åĵģ
    0.09
    Activations Density 0.419%

    No Known Activations