© 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. 57852
    Prev
    Next
    INDEX
    Explanations

    start of phrases or new topics

    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°¼äºļ
    -0.08
    ann
    -0.07
    ischt
    -0.07
    ç¼¥
    -0.07
    ä¸īéĩĮ
    -0.07
    icker
    -0.06
    rio
    -0.06
    NIS
    -0.06
    nam
    -0.06
    awi
    -0.06
    POSITIVE LOGITS
    就象
    0.07
    éĥ¨
    0.07
    esture
    0.07
    å¿ħè¦ģ
    0.07
     kehil
    0.07
    erdale
    0.06
    हà¥ĩ
    0.06
    æľĭåıĭ
    0.06
    (es
    0.06
     Kantor
    0.06
    Activations Density 0.070%

    No Known Activations