© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25095
    Prev
    Next
    INDEX
    Explanations

    ; punctuation

    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
    amedi
    -0.09
    ä¸įèĩª
    -0.09
    åIJĦ级åIJĦç±»
    -0.07
    avig
    -0.07
    ä¸įçģŃ
    -0.07
    èĿĩ
    -0.07
    èĭ¥ä¸įæĺ¯
    -0.07
    tested
    -0.07
    olith
    -0.06
    ä»»ä¸Ģ
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.09
    说åIJ§
    0.08
    åħĭåĬĽ
    0.07
     perms
    0.07
    jana
    0.07
    essar
    0.07
    ãģ£ãģ±ãĤĬ
    0.07
    zuk
    0.07
    amble
    0.07
    æľºçļĦ
    0.07
    Activations Density 0.034%

    No Known Activations