© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2371
    Prev
    Next
    INDEX
    Explanations

    term, Term

    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
    roh
    -0.06
    ohan
    -0.06
    æľīæĸĻ
    -0.06
    ITH
    -0.06
    ospace
    -0.06
    ç¡®æľī
    -0.06
    zone
    -0.06
    çł´
    -0.06
    icc
    -0.06
    æĸĻ
    -0.06
    POSITIVE LOGITS
    _TERM
    0.09
    å©ļ
    0.08
    <|box_end|>
    0.08
    Term
    0.08
    term
    0.08
    欣欣
    0.08
     term
    0.08
    standen
    0.08
    stand
    0.07
    Hyper
    0.07
    Activations Density 0.023%

    No Known Activations