© 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. 22384
    Prev
    Next
    INDEX
    Explanations

    angle and degree

    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
    çĪ½åı£
    -0.07
    åİŁåij³
    -0.07
     buch
    -0.07
    ités
    -0.07
    ýt
    -0.07
    çģ¾
    -0.07
    å¦ĤåĽł
    -0.07
    _nil
    -0.07
    æľīä»·åĢ¼
    -0.07
    ç³»æķ°
    -0.07
    POSITIVE LOGITS
    Sector
    0.09
     angles
    0.08
    ози
    0.08
     rotate
    0.08
     compass
    0.07
     rotates
    0.07
    .rotate
    0.07
    erc
    0.07
    æĹĭ转
    0.07
    æĸ¹ä½į
    0.07
    Activations Density 0.006%

    No Known Activations