© 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. 43556
    Prev
    Next
    INDEX
    Explanations

    data credit class tutorials company orbs

    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
    ä½ľåĪĻ
    -0.08
    unsch
    -0.08
    ä¸Ģåīij
    -0.07
    htable
    -0.07
    kony
    -0.07
    åĪĻåľ¨
    -0.07
    âĸ¶
    -0.07
    ächt
    -0.07
    iec
    -0.07
    åĪĻå°Ĩ
    -0.07
    POSITIVE LOGITS
    并éĿŀ
    0.11
    并ä¸į代表
    0.10
    ä¸įä»ħä»ħ
    0.10
    ä¸įä»ħä»ħæĺ¯
    0.09
    并éĿŀæĺ¯
    0.09
    ä¹Łä¸įä¸Ģå®ļ
    0.09
    è¿ĺæľīåħ¶ä»ĸ
    0.09
    并ä¸įæĺ¯
    0.08
    æľªå¿ħ
    0.08
    并ä¸įæĦıåij³çĿĢ
    0.08
    Activations Density 0.009%

    No Known Activations