© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39760
    Prev
    Next
    INDEX
    Explanations

    bullet points or special characters

    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
     respective
    -0.06
     Merry
    -0.06
    ***
    -0.06
    æīĢéľĢè¦ģ
    -0.05
    ovin
    -0.05
    ↵↵
    -0.05
    ä¸Ģåħ±
    -0.05
     Lut
    -0.05
    åľ¨æľ¬ç«Ļ
    -0.05
    åı¯éĢīä¸Ń
    -0.05
    POSITIVE LOGITS
    éĺ¿æĭī伯
    0.10
    æ¯Ľæ³½ä¸ľ
    0.10
    缸è¾ħ缸æĪIJ
    0.10
    俱ä¹IJéĥ¨
    0.09
    åĬłæĭ¿å¤§
    0.09
    ä¸įåı¯æĢĿè®®
    0.08
    æĸ°åĬłåĿ¡
    0.08
     sourceMappingURL
    0.07
    ä¸Ĭè¿ĩ
    0.07
    ä¸Ĭæŀ¶
    0.07
    Activations Density 0.006%

    No Known Activations