© 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. 19109
    Prev
    Next
    INDEX
    Explanations

    world.com

    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
    aking
    -0.10
    åĸĨ
    -0.09
    alled
    -0.09
    æľīä»·åĢ¼çļĦ
    -0.09
    ãĥ¯ãĥ¼ãĤ¯
    -0.08
    wan
    -0.08
    OfYear
    -0.08
    è¿Ļç¬Ķ
    -0.08
    æ²¼
    -0.08
    ç§ij室
    -0.08
    POSITIVE LOGITS
    wide
    0.10
    erg
    0.09
    涯
    0.09
    isas
    0.09
    ç¢ī
    0.09
    æĦļèł¢
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
     اÙĦØŃر
    0.08
    ubi
    0.08
     па
    0.08
    Activations Density 0.016%

    No Known Activations