© 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. 41913
    Prev
    Next
    INDEX
    Explanations

    varying levels, concentrations, doses, conditions

    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
    CP
    -0.08
    RP
    -0.07
    æ¶Ī
    -0.06
    igion
    -0.06
    igg
    -0.06
    erm
    -0.06
     Tepp
    -0.06
    ä¸ĩå¹´
    -0.06
    çĮ©
    -0.06
    WithType
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.12
    ä¸įåIJĮæŶ
    0.11
     varying
    0.11
     ranging
    0.11
     varied
    0.11
    vary
    0.11
    æĺ¯ä¸įåIJĮçļĦ
    0.10
    ä»İå°ıåĪ°å¤§
    0.10
    ä¸įåIJĮçļĦ
    0.10
    ä¸įåIJĮç¨ĭ度çļĦ
    0.10
    Activations Density 0.434%

    No Known Activations