© 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. 50296
    Prev
    Next
    INDEX
    Explanations

    describing related actions

    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
    جز
    -0.07
    atoon
    -0.07
    ัà¹Īว
    -0.07
    ordia
    -0.07
    .serialization
    -0.07
    CKET
    -0.06
    绾ç»İ
    -0.06
    actal
    -0.06
    ×ŀ×ķת
    -0.06
    ippers
    -0.06
    POSITIVE LOGITS
    注æĦıçļĦæĺ¯
    0.09
    icode
    0.08
    æľīä½Ļ
    0.08
    lessly
    0.08
    ỵ
    0.08
    y
    0.07
    ny
    0.07
    ysh
    0.07
    lese
    0.07
    ad
    0.07
    Activations Density 0.059%

    No Known Activations