© 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. 22731
    Prev
    Next
    INDEX
    Explanations

    "ackson" names

    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
    å®ĺ
    -0.10
    娣
    -0.09
    è¿ĺæĺ¯è¦ģ
    -0.09
    èĢ»
    -0.08
    åIJģ
    -0.08
    çĨ¨
    -0.08
     Rut
    -0.08
    åıªæľī
    -0.08
     Gross
    -0.08
    ÑĤоÑĢ
    -0.08
    POSITIVE LOGITS
    è·ŁæĪij
    0.12
    åľ¨æĪij
    0.12
    åľ¨æĪijçļĦ
    0.11
    è·ŁæĪij说
    0.11
    æ¯ĶæĪij
    0.10
    饮çĶ¨æ°´
    0.10
    ç»ĻäºĨæĪij
    0.10
    为æĪij们
    0.10
    ç»ĻæĪij们
    0.09
    帮æĪij
    0.09
    Activations Density 0.058%

    No Known Activations