© 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. 42701
    Prev
    Next
    INDEX
    Explanations

    node precession, spinner arrow, or throttle projection

    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
    isz
    -0.07
    itr
    -0.07
    ysize
    -0.07
    åĬłçļĦ
    -0.07
    éĩľ
    -0.07
    ogna
    -0.07
    undu
    -0.07
    æ°´æĺ¯
    -0.07
    é«ĺåİŁ
    -0.07
    BlockSize
    -0.07
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.10
    ä½įç½®
    0.09
     alignments
    0.09
     alignment
    0.09
    对åĩĨ
    0.09
     periodically
    0.09
    æĸ¹ä½į
    0.08
    åĽºå®ļ
    0.08
    çĽ¸å¯¹äºİ
    0.08
     rotating
    0.08
    Activations Density 0.041%

    No Known Activations