© 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. 30999
    Prev
    Next
    INDEX
    Explanations

    scientific citations

    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¯¹æľ¬æ¬¡
    -0.07
    ibas
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    viol
    -0.06
    ibur
    -0.06
    érit
    -0.06
    @email
    -0.06
    batim
    -0.06
    åĪ¶æĪIJçļĦ
    -0.06
    MF
    -0.06
    POSITIVE LOGITS
    èĵ®
    0.07
    \Context
    0.07
    楼顶
    0.07
    imak
    0.07
    าà¸ĩ
    0.07
    olor
    0.07
    ILLISE
    0.07
    屡
    0.07
    ilen
    0.06
    kong
    0.06
    Activations Density 0.001%

    No Known Activations