© 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. 2873
    Prev
    Next
    INDEX
    Explanations

    Southern gothic style

    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
    è¹Ī
    -0.10
    è¿Ļ个æĹ¶ä»£
    -0.10
    å°ĸåı«
    -0.09
     sexes
    -0.09
    çīĪæĿĥæīĢæľī
    -0.09
    ascript
    -0.09
    西æ¹ĸ
    -0.09
    èįĩ
    -0.08
    ango
    -0.08
    åı¤ä»£
    -0.08
    POSITIVE LOGITS
    asca
    0.10
    åı£æľį
    0.09
    人家
    0.09
    æ´ĭèij±
    0.08
     Cannon
    0.08
    è¾ĺ
    0.08
    style
    0.08
    sert
    0.08
    飫
    0.08
    alach
    0.08
    Activations Density 0.010%

    No Known Activations