© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8430
    Prev
    Next
    INDEX
    Explanations

    rotation and turning

    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
    usher
    -0.11
    åĻ¤
    -0.10
    缴æĴŃéĹ´
    -0.10
    obb
    -0.09
    orsch
    -0.09
    ingo
    -0.09
    usch
    -0.09
    æĬij
    -0.09
    æijĨ
    -0.09
    åĪĨæµģ
    -0.09
    POSITIVE LOGITS
    转åĬ¨
    0.13
    è¿IJ转
    0.13
    éĻĢ
    0.11
     spinning
    0.11
     spins
    0.11
    åĽ´ç»ķ
    0.10
    çļĦéĢŁåº¦
    0.10
    橹
    0.10
    .spin
    0.09
    大ä¼Ĺ
    0.09
    Activations Density 0.175%

    No Known Activations