© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    indicates or displays

    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
    isa
    -0.08
    iya
    -0.08
    tuk
    -0.07
    åı¯èĥ½åľ¨
    -0.07
    åı¯èĥ½å¯¼èĩ´
    -0.07
    åħ¼
    -0.07
     Trop
    -0.07
    大æ¦Ĥ
    -0.07
    Ø«
    -0.07
    icol
    -0.07
    POSITIVE LOGITS
    è¿Ļ表æĺİ
    0.20
    è¿Ļ说æĺİ
    0.18
    就说æĺİ
    0.17
    说æĺİ
    0.16
    表æĺİ
    0.14
    indic
    0.14
     indicating
    0.14
     indicative
    0.13
     indicates
    0.13
    说æĺİäºĨ
    0.12
    Activations Density 0.299%

    No Known Activations