© 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. 33304
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks or clauses

    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
    stad
    -0.07
    åħ¬æĬ¥
    -0.07
     Welch
    -0.07
    eware
    -0.07
    field
    -0.07
    ãĥ¼ãĤ¸ãĤ§
    -0.07
    绾ç»İ
    -0.07
    ERO
    -0.07
    èĤĩ
    -0.07
    æ¡ĤåĽŃ
    -0.06
    POSITIVE LOGITS
    çł´
    0.07
    移åĪ°
    0.07
    лÑİ
    0.07
    inaldo
    0.07
    ako
    0.07
    _integration
    0.07
     Ñĩо
    0.07
    ç¦ģ
    0.06
    æĺ¯ä¸ĢèĪ¬
    0.06
    otle
    0.06
    Activations Density 0.003%

    No Known Activations