© 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. 63179
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tures
    -0.09
    umber
    -0.09
    çĦ¶æĺ¯
    -0.09
    ered
    -0.08
    Ł
    -0.08
    sse
    -0.08
    gregate
    -0.08
    uant
    -0.07
    ses
    -0.07
    rup
    -0.07
    POSITIVE LOGITS
    ting
    0.11
    iz
    0.08
     einzelnen
    0.07
    æĥħåĨµä¸ĭ
    0.07
    ür
    0.07
     erreich
    0.07
    á»ijc
    0.07
    unks
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
    åľ¨æ¯ı个
    0.07
    Activations Density 0.000%

    No Known Activations