© 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. 41844
    Prev
    Next
    INDEX
    Explanations

    . followed by The, While, does, primary

    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
    out
    -0.07
    -0.07
    沧
    -0.07
    åı¤å±ĭ
    -0.06
     inval
    -0.06
     favor
    -0.06
    jos
    -0.06
    å½¢
    -0.06
    -0.06
    ä½İèĩ³
    -0.06
    POSITIVE LOGITS
    è¿ĶåĽŀé¦ĸ页
    0.07
    à¯Ĭ
    0.07
    ãģ¾ãģļ
    0.07
    ç¿ł
    0.07
    TRI
    0.07
    確ãģĭãģ«
    0.07
    [code
    0.07
    orne
    0.07
    书åIJ§
    0.07
    ource
    0.06
    Activations Density 0.013%

    No Known Activations