© 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. 56548
    Prev
    Next
    INDEX
    Explanations

    quarter financial results

    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
    aceous
    -0.09
    å¸Ń
    -0.09
    _tar
    -0.09
     Newman
    -0.09
    ideshow
    -0.09
    éĺ¶å±Ĥ
    -0.09
    ä¸įæĪIJ
    -0.09
    å½ĵå±Ģ
    -0.09
    ><![
    -0.09
    å±ĭ
    -0.09
    POSITIVE LOGITS
    å·¥ä½ľæĬ¥åijĬ
    0.10
    ç»ĵæĿŁåIJİ
    0.10
    以æĿ¥
    0.10
    æĪijå¸Ĥ
    0.09
    æĿ¥ä¸´
    0.09
    -most
    0.09
    -long
    0.09
    è¿ĩåIJİ
    0.09
    æľ«
    0.09
    åŃ£
    0.08
    Activations Density 0.008%

    No Known Activations