© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    adharnos; aadharnos;

    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
    à¸ķั
    -0.06
    teri
    -0.06
    Ĵ
    -0.06
    å¤§æ±Ł
    -0.06
    æĽ¸
    -0.06
    ×IJ×ķת
    -0.06
    okers
    -0.06
    assi
    -0.06
    inery
    -0.06
    ª
    -0.06
    POSITIVE LOGITS
    .getTransaction
    0.07
    AtPath
    0.07
    รà¸ģิà¸Ī
    0.07
    enco
    0.07
    amis
    0.06
    jou
    0.06
    å·¥ä½ľä¸ĬçļĦ
    0.06
    à¹Īาà¸Ļ
    0.06
    reh
    0.06
    insula
    0.06
    Activations Density 2.764%

    No Known Activations