© 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. 25680
    Prev
    Next
    INDEX
    Explanations

    spin exchange

    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
    ardi
    -0.07
    å®īåħ¨çļĦ
    -0.06
    camel
    -0.06
    elang
    -0.06
    è¿ĻäºĽæķ°æį®
    -0.06
    ulg
    -0.06
    æ¯Ķäºļ
    -0.06
    adu
    -0.06
     Sounds
    -0.06
    μι
    -0.06
    POSITIVE LOGITS
    æĹĭ
    0.09
    Spin
    0.08
    -spin
    0.08
    åľ¨ä¸Ģèµ·çļĦ
    0.08
     *–
    0.08
    spin
    0.08
    ottie
    0.08
     tán
    0.08
    дик
    0.07
    缸æīĭ
    0.07
    Activations Density 0.002%

    No Known Activations