© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7963
    Prev
    Next
    INDEX
    Explanations

    yet, contrasting statements

    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
     zwar
    -0.14
    èĻ½çĦ¶
    -0.11
    åĽºçĦ¶
    -0.10
    èĻ½çĦ¶æĺ¯
    -0.10
    едÑĮ
    -0.10
    äºİæĺ¯
    -0.09
     therefore
    -0.09
    èĢģå®ŀ
    -0.09
    åħĪæĺ¯
    -0.09
    ä¸įåĨį
    -0.09
    POSITIVE LOGITS
    ä¾ĿçĦ¶
    0.13
    ä»įæľª
    0.12
    ä¾Ŀæŧ
    0.11
     ë¶Ī구íķĺê³ł
    0.11
    ä»įçĦ¶
    0.11
    åģıåģı
    0.11
     STILL
    0.11
    ä¾ĿçĦ¶æĺ¯
    0.10
    liqu
    0.10
    æĢ»è§īå¾Ĺ
    0.09
    Activations Density 0.106%

    No Known Activations