© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    sector shape, FITC, Division II

    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
    -0.07
     (
    -0.07
    åģ¶
    -0.07
    SS
    -0.07
     Kor
    -0.06
    .
    -0.06
     [
    -0.06
    /
    -0.06
    çĪĨ
    -0.06
     "
    -0.05
    POSITIVE LOGITS
    _SID
    0.09
    ä¹Łå°±æĦıåij³çĿĢ
    0.08
    á»ĭa
    0.08
    onha
    0.08
    ogui
    0.08
    agi
    0.08
    è¿ĺä¸įæĺ¯
    0.08
    onese
    0.08
     pera
    0.08
    ãģ
    0.08
    Activations Density 0.005%

    No Known Activations