© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32867
    Prev
    Next
    INDEX
    Explanations

    spin/spun/spinner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿IJåĬ¨ä¼ļ
    -0.10
    arias
    -0.10
    æ®Ħ
    -0.09
    è·ŁçĿĢ
    -0.09
    ãģ¥
    -0.08
    .eof
    -0.08
    dden
    -0.08
    è§Į
    -0.08
    izon
    -0.08
    usch
    -0.08
    POSITIVE LOGITS
     spinning
    0.12
    -spin
    0.12
     spin
    0.11
     spun
    0.11
     spins
    0.11
    spinner
    0.11
     spinner
    0.10
    éĻĢ
    0.10
     Spinner
    0.10
     Spin
    0.10
    Activations Density 0.057%

    No Known Activations