© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    graduate of / from

    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
    å¾Ģ常ä¸Ģæł·
    -0.08
    lessly
    -0.08
    grave
    -0.08
    Ñģпол
    -0.08
    nement
    -0.07
    å¼Ģå¾Ĺ
    -0.07
     ê²Įëĭ¤ê°Ģ
    -0.07
    odore
    -0.07
    otime
    -0.07
    istian
    -0.07
    POSITIVE LOGITS
    uates
    0.09
    urally
    0.08
    wohl
    0.07
    ÑĭваеÑĤ
    0.07
    ModelIndex
    0.07
    åħ¸ç¦®
    0.07
    ural
    0.06
    rons
    0.06
    iles
    0.06
    olph
    0.06
    Activations Density 0.027%

    No Known Activations