© 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. 31937
    Prev
    Next
    INDEX
    Explanations

    norm vector, velocity, derivative

    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
    é«ĺæŀ¶
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
    ستاÙĨÛĮ
    -0.06
    _MISSING
    -0.06
    ush
    -0.06
    andex
    -0.06
    åıªè¦ģèĥ½
    -0.06
    मित
    -0.06
    çĭIJ
    -0.06
    пÑĢеÑģÑģ
    -0.06
    POSITIVE LOGITS
    -opt
    0.07
     derivative
    0.07
    /angular
    0.07
    olas
    0.07
    dpi
    0.07
    tud
    0.07
    slope
    0.07
    rate
    0.07
    InitialState
    0.07
     Kino
    0.07
    Activations Density 0.010%

    No Known Activations