© 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. 40778
    Prev
    Next
    INDEX
    Explanations

    is followed by programming terms

    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
    istet
    -0.08
    âu
    -0.07
    uccio
    -0.07
    ôi
    -0.07
    stry
    -0.07
    被èªī为
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    sterol
    -0.07
    以大
    -0.07
    éné
    -0.07
    POSITIVE LOGITS
    omorphic
    0.08
    ä¸ĢåĽŀäºĭ
    0.08
    å·¥ä½ľçĬ¶æĢģ
    0.08
    羣çļĦæľī
    0.07
    olation
    0.07
    ván
    0.07
    å·¥ä½ľæĪĸ
    0.07
    /is
    0.07
    subclass
    0.07
    .Has
    0.07
    Activations Density 0.059%

    No Known Activations