© 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. 22698
    Prev
    Next
    INDEX
    Explanations

    illumination and lighting

    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
    æ¼ł
    -0.11
    æ°Ķæģ¯
    -0.09
    å¼Ĥåľ°
    -0.09
    riba
    -0.09
    æ³
    -0.09
    _VERBOSE
    -0.08
    éĢĢç¨İ
    -0.08
    å°ıå·§
    -0.08
    é«ĺç´łè´¨
    -0.08
    订
    -0.08
    POSITIVE LOGITS
    çħ§
    0.13
    çħ§æĺİ
    0.12
    çħ§äº®
    0.11
    çĽĬ
    0.10
    ustr
    0.09
    æī¿åĬŀ
    0.09
    ä¸īæľŁ
    0.08
    çģ¯åħ·
    0.08
    åĵºä¹³
    0.08
    ä¸ĢåIJij
    0.08
    Activations Density 0.050%

    No Known Activations