© 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. 54095
    Prev
    Next
    INDEX
    Explanations

    By the time

    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
    çĭIJ
    -0.12
    çݳ
    -0.10
    å¾Īå¿«å°±
    -0.10
    ä¸įåĪ°
    -0.10
    æīĵå¼ĢäºĨ
    -0.09
    ä¸įåıĺ
    -0.09
    æĴ¼
    -0.09
    .addField
    -0.09
    è¿Ļä¸ĢåĪ»
    -0.09
    èĬ±æľµ
    -0.09
    POSITIVE LOGITS
    å·²æĺ¯
    0.12
    å·²ç»ıæĺ¯
    0.09
     already
    0.09
     anew
    0.08
    ä¸įä»ħä»ħæĺ¯
    0.08
     Cave
    0.08
    沧
    0.08
    scar
    0.08
    UPI
    0.08
    å·³
    0.08
    Activations Density 0.045%

    No Known Activations