© 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. 7559
    Prev
    Next
    INDEX
    Explanations

    max or upper bounds

    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
    minimum
    -0.09
    Minimum
    -0.08
     minimum
    -0.08
     Minimum
    -0.07
    boot
    -0.07
    足
    -0.07
    _minimum
    -0.07
     минимÑĥм
    -0.07
    orning
    -0.07
    rend
    -0.07
    POSITIVE LOGITS
    ä¸ĬéĻIJ
    0.14
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.12
    ä¸įè¶ħè¿ĩ
    0.11
    ä¸įèĥ½è¶ħè¿ĩ
    0.11
     Max
    0.11
    max
    0.11
     max
    0.11
    (max
    0.11
    çļĦæľĢ大
    0.11
    /max
    0.10
    Activations Density 0.055%

    No Known Activations