© 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. 26457
    Prev
    Next
    INDEX
    Explanations

    curvature

    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
    imizer
    -0.08
    áĥ£áĥłáĥĺ
    -0.08
    ek
    -0.08
    entifier
    -0.07
    owing
    -0.07
    interes
    -0.07
    hood
    -0.07
    ow
    -0.07
    ICATION
    -0.06
    eter
    -0.06
    POSITIVE LOGITS
    vature
    0.10
    iously
    0.09
    zec
    0.09
    less
    0.09
    ernt
    0.09
    æľīèĩ´
    0.09
    iosity
    0.08
    ÑĢио
    0.08
    roc
    0.08
    ulence
    0.08
    Activations Density 0.014%

    No Known Activations