© 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. 58054
    Prev
    Next
    INDEX
    Explanations

    warnings

    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
    ãģĤãģ£ãģ¦
    -0.09
    æĢİä¹Īåı¯èĥ½
    -0.09
    adow
    -0.09
    ä¸įå¾Ĺä¸į说
    -0.09
    æī¹
    -0.09
    .ascii
    -0.09
    rais
    -0.09
    æĺ¯ä¸įåı¯èĥ½
    -0.09
    BK
    -0.09
    没æľīå¿ħè¦ģ
    -0.09
    POSITIVE LOGITS
    sey
    0.10
     semiclass
    0.09
    iri
    0.09
    å¸Ń
    0.09
    åı¯èĥ½ä¼ļ
    0.08
    ä¼ļè®©ä½ł
    0.08
    足足
    0.08
    ovsky
    0.08
    lero
    0.08
    ä¸ĢåĪĨ
    0.08
    Activations Density 0.068%

    No Known Activations