© 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. 62240
    Prev
    Next
    INDEX
    Explanations

    æ°£æ°£æº £è¯´

    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
     justru
    -0.10
    ½
    -0.09
    áĥ£áĥļ
    -0.08
    opsis
    -0.08
    geist
    -0.08
    ipel
    -0.07
    oids
    -0.07
    åĩĢåĪ©æ¶¦ä¸º
    -0.07
    combo
    -0.07
    rippling
    -0.07
    POSITIVE LOGITS
    常说çļĦ
    0.11
    ingly
    0.10
    ä»ĸäºĨ
    0.09
    ness
    0.09
    nement
    0.09
    ä¸įåIJĮäºĨ
    0.08
    ë°Ķë¡ľ
    0.08
    ä¸įéĶĻäºĨ
    0.08
    è¿Ļ个éģĵçIJĨ
    0.08
    éĹ®é¢ĺäºĨ
    0.08
    Activations Density 0.002%

    No Known Activations