© 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. 57150
    Prev
    Next
    INDEX
    Explanations

    hit-and-run

    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
    éļ¾éģĵ
    -0.09
    究
    -0.08
    elman
    -0.08
    æŁ°
    -0.08
    èħ»
    -0.08
    alin
    -0.08
    é»Ħèī²
    -0.08
    è¿ijæľŁ
    -0.08
    nee
    -0.08
     cardio
    -0.08
    POSITIVE LOGITS
    汶
    0.10
    çļĦæĦŁæĥħ
    0.10
    ä»»ä½ķ人éĥ½
    0.10
    æľīæĿ¡ä»¶
    0.09
    çIJIJ
    0.09
    arking
    0.09
    sites
    0.09
    หลวà¸ĩ
    0.09
    æĭ¼
    0.09
    ä»Ĺ
    0.09
    Activations Density 0.001%

    No Known Activations