© 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. 22144
    Prev
    Next
    INDEX
    Explanations

    places of organizations

    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
    å´ĩ
    -0.10
    ervo
    -0.10
    alla
    -0.09
    ãģĹãģ£
    -0.09
    ä¸įåĪ°
    -0.09
    dorf
    -0.08
    amba
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    å´ĩé«ĺ
    -0.08
    2
    -0.08
    POSITIVE LOGITS
    å¸®ä½ł
    0.11
    å®ĺæĸ¹
    0.10
    æĪĸèĢħ
    0.10
    æĪĸæĺ¯
    0.10
    éĤ£ç§į
    0.09
    æ¯Ķå¦Ĥ说
    0.09
    æĪĸèĢħæĺ¯
    0.09
    éĢļ常
    0.09
    åľ°æ¯¯
    0.09
     or
    0.09
    Activations Density 0.127%

    No Known Activations