© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    can, should, need, have to

    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
    aven
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.07
    ç«Łæĺ¯
    -0.07
    ENDA
    -0.07
    çķĮ
    -0.07
     unforgettable
    -0.07
    ehm
    -0.07
    Äįnih
    -0.07
    brand
    -0.06
    转载èĩ³
    -0.06
    POSITIVE LOGITS
    oret
    0.08
    oretical
    0.08
    ко
    0.07
     Colo
    0.07
    çŃīå¥ĸ
    0.07
    ...\
    0.06
    pb
    0.06
     ÑģпÑĸ
    0.06
    æ§ĺ
    0.06
    åģļçļĦå°±æĺ¯
    0.06
    Activations Density 0.092%

    No Known Activations