© 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. 57721
    Prev
    Next
    INDEX
    Explanations

    date and location information

    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
    awat
    -0.08
    empl
    -0.08
    erno
    -0.07
    åŃ¦æł¡é¢Ĩ导
    -0.07
    女æĢ§æľĭåıĭ
    -0.07
    éĥijéĩį声æĺİ
    -0.07
    ä¹İåħ¶
    -0.07
     Ñģимп
    -0.07
    itational
    -0.07
    妨
    -0.07
    POSITIVE LOGITS
    é¹
    0.07
    iro
    0.06
    LL
    0.06
    IP
    0.06
    è®©æĽ´å¤ļçļĦ人
    0.06
    éĹ²
    0.06
    ä¸įè´Łè´£
    0.06
    人éĹ´
    0.06
    çĥŃçĤ¹
    0.06
    Tau
    0.06
    Activations Density 0.004%

    No Known Activations