© 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. 31063
    Prev
    Next
    INDEX
    Explanations

    .rc file extensions and paths

    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
    (","
    -0.09
    ä¸ĢæĿ¡é¾Ļ
    -0.07
    oze
    -0.07
    داÙħ
    -0.07
    hern
    -0.07
    ä¼ĺ
    -0.07
    (','
    -0.07
    è°ĥçłĶåijĺ
    -0.06
    (CONT
    -0.06
    (OP
    -0.06
    POSITIVE LOGITS
    .sqlite
    0.08
    .rc
    0.07
    ington
    0.07
    agas
    0.07
    ah
    0.07
    rc
    0.06
    åĢ¼å¾Ĺ
    0.06
    bage
    0.06
    å¢ĥåľ°
    0.06
    æľ¬åĬŀæ³ķ
    0.06
    Activations Density 0.806%

    No Known Activations