© 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. 39467
    Prev
    Next
    INDEX
    Explanations

    URLs and tech terms

    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
    æľĢæĸ°æĽ´æĸ°
    -0.07
    -ignore
    -0.07
    å°¼äºļ
    -0.07
    osa
    -0.07
    åİĨåı²æĢ§
    -0.07
    offs
    -0.06
    ķĮ
    -0.06
    usak
    -0.06
    è´¢
    -0.06
    /tab
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĿãģ®
    0.09
    åıĬåħ¶
    0.08
    ä¸İåħ¶
    0.07
    åĴĮä»ĸçļĦ
    0.07
    ãĢħ
    0.07
    andu
    0.07
    è¿ĻäºĽéĹ®é¢ĺ
    0.07
    å¦Ĥåħ¶
    0.07
     adh
    0.06
    [email
    0.06
    Activations Density 0.040%

    No Known Activations