© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21434
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    å¹²éĥ¨
    -0.09
    çĪ±ç¾İ
    -0.08
    atel
    -0.08
     Sweat
    -0.08
    udes
    -0.08
    缴æĴŃéĹ´
    -0.08
    çľ¾
    -0.08
    ç³Ļ
    -0.08
    privileged
    -0.08
    åĮħåĮħ
    -0.08
    POSITIVE LOGITS
    ä¸ĢéŨ
    0.11
    æĺ¯ä¸Ģéĥ¨
    0.10
    ä¸įä»ħæĺ¯
    0.10
     Whitney
    0.09
    çļĦçIJĨæĥ³
    0.09
    è¦ģä¹Ī
    0.09
    ä¸Ģ缴éĥ½æĺ¯
    0.09
    æĺ¯ä¸ª
    0.09
    æĸĻ
    0.09
    ixe
    0.09
    Activations Density 0.150%

    No Known Activations