© 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. 32743
    Prev
    Next
    INDEX
    Explanations

    spin

    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
    æĤ¬æ®Ĭ
    -0.07
    èĶĹ
    -0.07
    åı¯èĥ½éĢłæĪIJ
    -0.07
    æ½¼
    -0.06
    ulin
    -0.06
    è¡ĮéĹ´
    -0.06
    ç³ĸå°¿çĹħæĤ£èĢħ
    -0.06
     Diabetes
    -0.06
    ersh
    -0.06
    éĩij马
    -0.06
    POSITIVE LOGITS
    -spin
    0.11
     spin
    0.11
    Spin
    0.10
    ä¸īç»´
    0.10
     spins
    0.10
    spin
    0.10
     Spin
    0.09
     spinning
    0.09
     coordinates
    0.09
    _spin
    0.09
    Activations Density 0.008%

    No Known Activations