© 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. 43401
    Prev
    Next
    INDEX
    Explanations

    separators followed by common words

    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
    åĬłæĭ¿å¤§
    -0.11
    åĭĩå¾Ģ缴åīį
    -0.10
    æĸ°åĬłåĿ¡
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
     thereby
    -0.08
    à¸Ĺà¹Į
    -0.07
     thus
    -0.07
    ä»İèĢĮ
    -0.06
     hence
    -0.06
    èĢĮåľ¨
    -0.06
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.09
    ripp
    0.08
    Õ¸ÖĢ
    0.08
    னி
    0.08
    νοÏį
    0.08
    ãĥ«ãĥī
    0.07
     Cidad
    0.07
    olla
    0.07
    è¾ķ
    0.07
    tex
    0.07
    Activations Density 0.488%

    No Known Activations