© 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. 26043
    Prev
    Next
    INDEX
    Explanations

    assignment and increment/decrement

    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
    zan
    -0.09
    è¹´
    -0.08
    è´¸
    -0.08
    åħ³äºĨ
    -0.08
    ×Ļת×Ļ
    -0.08
    æĭīå¼ĢäºĨ
    -0.08
    /cc
    -0.07
    kis
    -0.07
    .createTextNode
    -0.07
    ä¿ĥåıijå±ķ
    -0.07
    POSITIVE LOGITS
     -=
    0.06
    éļ¾å¾Ĺ
    0.06
    Ãły
    0.06
     read
    0.06
     Epstein
    0.06
    ç´¯
    0.06
    resident
    0.06
    иÑĤоÑĢ
    0.06
     +=
    0.06
     opinion
    0.06
    Activations Density 0.027%

    No Known Activations