© 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. 42991
    Prev
    Next
    INDEX
    Explanations

    representation, twisted, diagonal, loop

    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
    æĹłéĩı
    -0.08
    è¿Ļç±»
    -0.07
     nav
    -0.06
    太ä»ĵ
    -0.06
    hdr
    -0.06
    nav
    -0.06
    è¿ľæ´ĭ
    -0.06
    åĽ½å®¶åĴĮåľ°åĮºçļĦ
    -0.06
     Hip
    -0.06
    æĭ¦ä½ı
    -0.06
    POSITIVE LOGITS
    aramel
    0.08
    å§ĭèĩ³
    0.07
    ogle
    0.07
     AppConfig
    0.07
    KeySpec
    0.07
    ä¸įå·®
    0.07
    .loop
    0.07
    ulas
    0.07
     twisting
    0.07
    loop
    0.07
    Activations Density 0.005%

    No Known Activations