© 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. 48363
    Prev
    Next
    INDEX
    Explanations

    integer types, size, or counts

    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
    .oracle
    -0.08
    atica
    -0.08
    auer
    -0.08
    çĽ¸çŁ¥
    -0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
    omie
    -0.07
    çļĭ
    -0.07
    è¯ī
    -0.07
    upro
    -0.07
    orris
    -0.07
    POSITIVE LOGITS
    cant
    0.08
    åħ¶
    0.07
    Cancelable
    0.07
    éci
    0.06
    ptime
    0.06
    _t
    0.06
    çĭĤ
    0.06
    æħ¢
    0.06
    icot
    0.06
     koll
    0.06
    Activations Density 0.037%

    No Known Activations