© 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. 35673
    Prev
    Next
    INDEX
    Explanations

    university addresses

    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
     конкÑĥÑĢÑģ
    -0.08
    steen
    -0.08
    è®°èĢħåľ¨
    -0.08
    è·¡
    -0.08
    uing
    -0.07
    éĺ¿å§¨
    -0.07
    avel
    -0.07
    æĪijå¦Ī
    -0.07
    tw
    -0.07
    æĥĬ
    -0.07
    POSITIVE LOGITS
    ãĢĴ
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.10
    æ¤Ĵ
    0.10
    -widgets
    0.10
     голов
    0.10
    èĸĦå¼±
    0.10
    пло
    0.09
    秩
    0.09
     ÙĪعÙĨ
    0.09
     Grants
    0.09
    Activations Density 0.143%

    No Known Activations