© 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. 29557
    Prev
    Next
    INDEX
    Explanations

    sentence beginning

    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
     o
    -0.06
    æ§Ľ
    -0.06
    èĭ
    -0.06
    ä¿ĥ
    -0.06
    èĭ¥
    -0.06
    mw
    -0.06
    ONIO
    -0.06
    åįĥéĩĮ
    -0.06
    o
    -0.06
    icker
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    ály
    0.08
    ä¸įæĸŃæĽ´æĸ°
    0.07
    ván
    0.07
    anna
    0.07
    æĥļ
    0.07
    åĪģ
    0.07
    tvr
    0.07
    ÏĦÏī
    0.07
    /misc
    0.07
    Activations Density 0.066%

    No Known Activations