© 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. 55252
    Prev
    Next
    INDEX
    Explanations

    just, seems, may, cannot

    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
     конеÑĩно
    -0.10
    æľĢåĸľæ¬¢
    -0.09
    èī¯å¥½
    -0.09
    _brightness
    -0.09
    èĪ¬
    -0.09
    æī©
    -0.08
    åĽłä¸ºæĪij
    -0.08
    ç²¾ç¾İ
    -0.08
     же
    -0.08
    atrice
    -0.08
    POSITIVE LOGITS
    以èĩ³äºİ
    0.17
    çĶļèĩ³
    0.12
    çĶļèĩ³æĺ¯
    0.11
    æģ¨ä¸įå¾Ĺ
    0.10
    à¸Ńà¸ģ
    0.10
     even
    0.10
    even
    0.10
    以èĩ´
    0.10
    è½»æĺĵ
    0.09
    æĬĬå®ĥ
    0.09
    Activations Density 0.051%

    No Known Activations