© 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. 13267
    Prev
    Next
    INDEX
    Explanations

    size, diameter, speed, width

    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
    ä¸įè¶ħè¿ĩ
    -0.10
    ä¸įèĥ½è¶ħè¿ĩ
    -0.09
    Unchecked
    -0.08
    渴
    -0.08
    à¹Ħมà¹Īà¹Ģà¸ģิà¸Ļ
    -0.08
    è¾¾æĪIJä¸Ģèĩ´
    -0.08
    æ»ĭ
    -0.07
    hurst
    -0.07
    æķ´æ²»å·¥ä½ľ
    -0.07
    è¿ĩéĩį
    -0.07
    POSITIVE LOGITS
    è¶³å¤Ł
    0.15
     sufficient
    0.14
    è¶³å¤ŁçļĦ
    0.13
     adequate
    0.13
    åħħ足
    0.12
     minimum
    0.12
    è¶³å¤ł
    0.12
     enough
    0.12
     sufficiently
    0.12
    minimum
    0.12
    Activations Density 0.186%

    No Known Activations