© 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. 62450
    Prev
    Next
    INDEX
    Explanations

    non-English characters and punctuation

    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
     dran
    -0.07
    åij»
    -0.07
    /Area
    -0.07
    æĢ¥äºĨ
    -0.07
    åįķæĬĹ
    -0.07
     "_"
    -0.07
    çĤİé»Ħ
    -0.07
    urv
    -0.07
    èĩªèº«é£İéĻ©
    -0.07
    ccion
    -0.07
    POSITIVE LOGITS
    çĦī
    0.07
    æ½¢
    0.06
    å¿«
    0.06
    ¯
    0.06
    ibly
    0.06
    ä¸įè§ģ
    0.06
     kuin
    0.06
    大æĦı
    0.06
    leston
    0.06
     taboo
    0.06
    Activations Density 0.042%

    No Known Activations