© 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. 40535
    Prev
    Next
    INDEX
    Explanations

    packages and paths

    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
    ular
    -0.07
    ếp
    -0.06
    á»ĵ
    -0.06
    ihan
    -0.06
    Äħż
    -0.06
    ãĥ«ãĤ¯
    -0.06
    irate
    -0.06
    æĪĸä¸İ
    -0.06
    ã
    -0.06
    chien
    -0.06
    POSITIVE LOGITS
    沫
    0.08
    ady
    0.07
    CLU
    0.07
    ãģİ
    0.07
    bygg
    0.07
    æ¦Ħ
    0.07
    (("
    0.06
    GENER
    0.06
    Ïħνα
    0.06
    ersions
    0.06
    Activations Density 0.012%

    No Known Activations