© 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. 35921
    Prev
    Next
    INDEX
    Explanations

    football positions defensive tackles rush end

    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
    wing
    -0.10
    楯
    -0.09
    #__
    -0.09
    éĻĮ
    -0.09
    åŀĵ
    -0.08
    é¹ij
    -0.08
    éªijåħµ
    -0.08
     Arb
    -0.08
    æµ·åĨĽ
    -0.08
    @[
    -0.08
    POSITIVE LOGITS
    éģģ
    0.10
    æĿ¡ä¾ĭ
    0.10
    æĻĴ
    0.09
     Garner
    0.09
     Stat
    0.09
    è¢Ń
    0.08
    æ§
    0.08
    迷失
    0.08
    INAL
    0.08
    anned
    0.08
    Activations Density 0.248%

    No Known Activations