© 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. 7506
    Prev
    Next
    INDEX
    Explanations

    code constructs and file extensions

    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
    oman
    -0.08
    nell
    -0.07
    ระ
    -0.07
    FTA
    -0.07
    OutOfRange
    -0.07
    ndon
    -0.07
    ÙĪاÙģ
    -0.07
    ä¸Ģéĥİ
    -0.07
    第äºĮéĺ¶æ®µ
    -0.07
    СÐĺ
    -0.07
    POSITIVE LOGITS
    详ç»Ĩæııè¿°
    0.08
     composed
    0.08
     consist
    0.07
    çļĦ详ç»Ĩ
    0.07
     consisting
    0.07
    åįĥçĻ¾
    0.07
    èĬ®
    0.07
    大æľī
    0.07
    composed
    0.07
    ä¸ĭè¿°
    0.06
    Activations Density 0.432%

    No Known Activations