© 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. 51410
    Prev
    Next
    INDEX
    Explanations

    descriptions of places and entities

    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
    çĶŁæ¶¯
    -0.09
     помеÑī
    -0.08
    æµģ浪
    -0.08
    æģ°æģ°
    -0.08
    ä½Ĩæĺ¯æĪij
    -0.08
     cpt
    -0.08
    件
    -0.07
    çīµ
    -0.07
    IVED
    -0.07
    æĸŃ
    -0.07
    POSITIVE LOGITS
    ç»ıèIJ¥èĮĥåĽ´
    0.12
    ç¾½æ¯Ľ
    0.11
    fans
    0.11
    æĭĽèģĺä¿¡æģ¯
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
    æīĢåľ¨åľ°
    0.10
    å®ŀåĬĽ
    0.10
    æĤ¼
    0.10
    å¥ĭæĸĹ缮æłĩ
    0.10
    ĥģ
    0.10
    Activations Density 0.008%

    No Known Activations