© 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. 33980
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or code snippets

    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
    è¿Ļ个éģĵçIJĨ
    -0.06
    ä¸İå®ŀéĻħ
    -0.06
     Z
    -0.06
    TypeEnum
    -0.06
    临è¿ij
    -0.06
     mo
    -0.06
    -0.06
    è¿Ļ个æķ°åŃĹ
    -0.06
    è±ģçĦ¶
    -0.06
     N
    -0.06
    POSITIVE LOGITS
     Gür
    0.09
    å¹³åĩ¡çļĦ
    0.08
    æ³Ľ
    0.08
    ãĤ·ãĥĥãĥĹ
    0.08
    oola
    0.08
    ollipop
    0.08
    å¤Ń
    0.08
     noop
    0.08
    西山
    0.08
    ypo
    0.08
    Activations Density 0.009%

    No Known Activations