© 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. 23797
    Prev
    Next
    INDEX
    Explanations

    global organization

    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
    าว
    -0.08
    zij
    -0.07
    forder
    -0.07
    å®ŀåľ¨æĺ¯
    -0.07
    åıªåı¯æĥľ
    -0.07
    eliti
    -0.07
    åıijèĩª
    -0.07
    asm
    -0.07
    others
    -0.06
    asser
    -0.06
    POSITIVE LOGITS
    izr
    0.08
    çļĦæŶåĢĻä¼ļ
    0.07
    éĹ®é¢ĺæĿ¥äºĨ
    0.07
    ubil
    0.07
    olis
    0.07
    ux
    0.07
    äk
    0.07
    otics
    0.06
    lov
    0.06
    _BYTE
    0.06
    Activations Density 0.001%

    No Known Activations