© 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. 34409
    Prev
    Next
    INDEX
    Explanations

    all options or zero values

    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
    TU
    -0.07
    bff
    -0.07
    BC
    -0.07
    adoras
    -0.07
    à°¤à±į
    -0.07
    è¿Ļè¿ĺæĺ¯
    -0.07
    دد
    -0.07
    rica
    -0.07
    为己任
    -0.07
    ẹo
    -0.07
    POSITIVE LOGITS
    åĪĻ表示
    0.09
     special
    0.08
     signify
    0.08
     sentinel
    0.08
    çŃīçī¹æ®Ĭ
    0.08
     specials
    0.07
    çī¹æ®ĬçļĦ
    0.07
    æĹ¥è¡¨ç¤º
    0.07
     Special
    0.07
    æĿ¥è¡¨ç¤º
    0.07
    Activations Density 0.108%

    No Known Activations