© 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. 11223
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    éĽĨåĽ¢åħ¬åı¸
    -0.09
    Grace
    -0.08
     Marvin
    -0.08
    è§ŀ
    -0.08
    CAPE
    -0.08
    itim
    -0.08
    çĭŀ
    -0.08
     Spo
    -0.08
    éĿ¢åŃIJ
    -0.08
    gov
    -0.08
    POSITIVE LOGITS
    èĢĹ
    0.09
    åѱ
    0.09
    æѤæĸĩ
    0.08
    fel
    0.08
    ä½ľä¸ºä¸ĢåIJį
    0.08
    ł
    0.08
    å°ĸ
    0.08
     ABS
    0.08
    饱
    0.08
    opol
    0.08
    Activations Density 0.062%

    No Known Activations