© 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. 23285
    Prev
    Next
    INDEX
    Explanations

    produced by

    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
    shaw
    -0.07
    esc
    -0.07
    æľĢéĩįè¦ģçļĦ
    -0.07
    jsc
    -0.07
    èĥĨ
    -0.06
    çĹ´
    -0.06
    xcb
    -0.06
    ç¿ł
    -0.06
    殿
    -0.06
    ties
    -0.06
    POSITIVE LOGITS
    Ú¯ÛĮر
    0.07
    å¥İ
    0.07
    igmoid
    0.07
    ×Ļ׾×ķ
    0.07
    ilh
    0.07
    ÏģÏĩ
    0.07
    æĪijåĪļ
    0.07
    iÅĤ
    0.07
    红çļĦ
    0.07
    åįļ
    0.07
    Activations Density 0.064%

    No Known Activations