© 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. 7191
    Prev
    Next
    INDEX
    Explanations

    on this site

    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
    åݻ买
    -0.10
    æīĵæĸŃ
    -0.10
    ä»ĸä»¬åľ¨
    -0.10
    åįłé¢Ĩ
    -0.09
    è´¥
    -0.09
    éªħ
    -0.09
    ocs
    -0.09
    å¼Ń
    -0.09
    æĺ¨å¤©
    -0.09
    èįł
    -0.09
    POSITIVE LOGITS
     данном
    0.08
    ä»ĺåĩº
    0.08
    .bundle
    0.08
    'icon
    0.08
    注éĩį
    0.08
     наÑĪем
    0.08
    ä½ľåĵģåĨħ容
    0.07
    横
    0.07
     cigar
    0.07
    çĨ¨
    0.07
    Activations Density 0.021%

    No Known Activations