© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    $(x, . ., )=$

    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
    ekan
    -0.07
    rops
    -0.07
    åľ¨å¤ĸ
    -0.06
     liber
    -0.06
    å¹´èĢģ
    -0.06
     aantal
    -0.06
    orm
    -0.06
    _mB
    -0.06
    mons
    -0.06
    _mA
    -0.06
    POSITIVE LOGITS
    agas
    0.09
    ampling
    0.08
    rint
    0.08
    åįĬå¤ľ
    0.08
    heatmap
    0.08
    리ìĸ´
    0.08
    ìĥĺ
    0.07
    äºĶåįĥå¹´
    0.07
    utine
    0.07
    Sampling
    0.07
    Activations Density 0.002%

    No Known Activations