© 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. 7737
    Prev
    Next
    INDEX
    Explanations

    italics indicates

    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
    ä½ķä¸į
    -0.07
     Quantum
    -0.07
    inou
    -0.06
    atar
    -0.06
     deserving
    -0.06
     Stud
    -0.06
    éģĹ
    -0.06
     quantum
    -0.06
    angu
    -0.06
    æ³ī
    -0.06
    POSITIVE LOGITS
    åĪĻ表示
    0.14
    æĹ¶è¡¨ç¤º
    0.12
     indicates
    0.12
     signifies
    0.12
    表æĺİ
    0.11
     signify
    0.10
     Indicates
    0.10
    è¿ĺ表示
    0.10
     indicating
    0.10
     indicate
    0.09
    Activations Density 0.063%

    No Known Activations