© 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. 30646
    Prev
    Next
    INDEX
    Explanations

    comman.php or man

    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
    RF
    -0.07
    P
    -0.07
    ent
    -0.06
    lice
    -0.06
    a
    -0.06
    å¾Īç®Ģåįķ
    -0.06
    k
    -0.06
    举起
    -0.06
     dict
    -0.06
    /packages
    -0.06
    POSITIVE LOGITS
    ãĥªãĤ¨
    0.10
    hani
    0.08
    leftright
    0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.08
    ç´Ĭ
    0.08
    глÑĥ
    0.08
    ToDevice
    0.08
    tility
    0.08
    pedo
    0.07
    вÑĮÑİ
    0.07
    Activations Density 0.002%

    No Known Activations