© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    the followed by ordinal or sequential words

    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
    åIJĦæľī
    -0.10
    èĦijåŃIJ
    -0.09
    åĢĴæĺ¯
    -0.09
    讽
    -0.09
    æľīä»·åĢ¼
    -0.09
    éķ¿çĽ¸
    -0.09
    Lifetime
    -0.09
    CADE
    -0.09
     thù
    -0.09
    æ¢ĥ
    -0.09
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.10
    çļĦä¸Ģ个
    0.09
     unfortunate
    0.09
    าะ
    0.08
    æĺİç¡®äºĨ
    0.08
    éĻªä¼´
    0.08
    ä¸Ģç§į
    0.08
    迤
    0.08
    .lazy
    0.08
    unic
    0.08
    Activations Density 0.136%

    No Known Activations