© 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. 44089
    Prev
    Next
    INDEX
    Explanations

    four

    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
    arine
    -0.08
    allo
    -0.07
     ÙĤÙĦ
    -0.07
    rand
    -0.07
    orna
    -0.07
    icol
    -0.07
    hold
    -0.07
    èµ°ä¸ĭåİ»
    -0.06
    æľīæĥħ
    -0.06
    ello
    -0.06
    POSITIVE LOGITS
    cke
    0.08
     various
    0.07
    åIJĦç§į
    0.07
    lotte
    0.07
    å½¼
    0.07
     Various
    0.07
     diversas
    0.07
    koz
    0.07
    å¿«åĪ°
    0.06
    å°½èĩªå·±
    0.06
    Activations Density 0.180%

    No Known Activations