© 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. 38595
    Prev
    Next
    INDEX
    Explanations

    Kar prefix

    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
    adak
    -0.09
    ļĮ
    -0.08
    ä¸į离
    -0.07
    волÑĮ
    -0.07
    apia
    -0.07
     surrounds
    -0.07
    çķĶ
    -0.06
     rives
    -0.06
    身ä¸Ĭä¸ĭ
    -0.06
    ä¿ĺèĻı
    -0.06
    POSITIVE LOGITS
    æį£
    0.08
     contribution
    0.08
     Contribution
    0.08
    è´¡çĮ®
    0.07
    çļĦè´¡çĮ®
    0.07
     diminishing
    0.07
    ä¸ĭä¸Ģ级
    0.07
    人éģĵ
    0.07
    urd
    0.07
    ç¬ijå¾Ĺ
    0.07
    Activations Density 0.001%

    No Known Activations