© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    keywords and tags

    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
    ftype
    -0.07
    èĩªæµģ
    -0.07
    Matchers
    -0.07
    ÙIJÙħ
    -0.07
    èĢĥè¯ķç½ij
    -0.07
    kana
    -0.07
    æĦıæ°Ķ
    -0.07
    人马
    -0.07
    ucken
    -0.07
    eby
    -0.06
    POSITIVE LOGITS
    jord
    0.07
     Serv
    0.06
    cede
    0.06
     Passage
    0.06
    ä¸ĥéĩĮ
    0.06
    ots
    0.06
    عب
    0.06
    izzo
    0.06
    åı¥ä¸Ń
    0.06
    以身
    0.06
    Activations Density 0.030%

    No Known Activations