© 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. 22595
    Prev
    Next
    INDEX
    Explanations

    angle and direction

    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
    æĹ¶ä»£çļĦ
    -0.08
    æĹłä¸Ĭ
    -0.07
    æĹ¶ä»£
    -0.07
    å±ĤçļĦ
    -0.07
     ton
    -0.07
    顶å±Ĥ
    -0.06
    订
    -0.06
     sez
    -0.06
     ab
    -0.06
    ton
    -0.06
    POSITIVE LOGITS
    imuth
    0.09
    hoek
    0.09
    åĪģ
    0.09
     ninety
    0.09
     angles
    0.09
    èĦ¸
    0.08
    зен
    0.08
     ë°©íĸ¥
    0.08
    æķ£å°Ħ
    0.08
    angle
    0.08
    Activations Density 0.007%

    No Known Activations