© 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. 57782
    Prev
    Next
    INDEX
    Explanations

    download software or files

    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
    ä¸ĭè½½
    -0.10
    èıŁ
    -0.09
    iani
    -0.09
    æݸ
    -0.08
     ÑģкаÑĩ
    -0.08
    æ²IJ
    -0.08
    ilib
    -0.08
    çļĦåŃĺåľ¨
    -0.08
    éªł
    -0.08
    ä¹Łä¸º
    -0.08
    POSITIVE LOGITS
    sla
    0.10
     zÅĤ
    0.10
     yarı
    0.10
    稿
    0.10
    ä¸įåĪ°
    0.10
    éĥ¨ä»¶
    0.09
    该æ¡Ī
    0.09
    绳
    0.09
    ALK
    0.09
    alker
    0.08
    Activations Density 0.023%

    No Known Activations