© 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. 49004
    Prev
    Next
    INDEX
    Explanations

    list index or count

    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
    dre
    -0.08
     trám
    -0.08
    ey
    -0.07
    joj
    -0.07
     Goldman
    -0.07
    _PRINTF
    -0.07
    chien
    -0.07
    icat
    -0.07
    bet
    -0.07
    rame
    -0.07
    POSITIVE LOGITS
    缮æłĩ
    0.07
    olulu
    0.06
     closer
    0.06
     cerebr
    0.06
     exact
    0.06
    -my
    0.06
    æĽ´è¡£
    0.06
    ental
    0.06
     ÙĪاÙĤعÛĮ
    0.06
    æĥ³è¦ģçļĦ
    0.06
    Activations Density 0.002%

    No Known Activations