© 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. 55892
    Prev
    Next
    INDEX
    Explanations

    perfectly/very degree adverb + adjective/adverb

    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
    lass
    -0.10
    è¿IJæ°Ķ
    -0.09
    Heroes
    -0.09
    ç»IJ
    -0.09
    æ§Ľ
    -0.09
    .guard
    -0.09
     gar
    -0.09
    æľĢåĸľæ¬¢çļĦ
    -0.08
    gar
    -0.08
    ä¸ĢåľĪ
    -0.08
    POSITIVE LOGITS
    å®Įåħ¨åı¯ä»¥
    0.19
    æĺ¯åı¯ä»¥
    0.12
     вполне
    0.12
    æľīåı¯èĥ½
    0.12
     possibility
    0.11
    åı¯èĥ½æĢ§
    0.11
     mümk
    0.10
    åĿį
    0.10
    æľīåħ´è¶£
    0.10
     khả
    0.10
    Activations Density 0.020%

    No Known Activations