© 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. 58698
    Prev
    Next
    INDEX
    Explanations

    manufacturing and technologies

    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
    æĻļæĬ¥
    -0.10
    è´´
    -0.09
    é¸Ń
    -0.09
    ren
    -0.08
    çŁ³æ²¹åĮĸå·¥
    -0.08
    ondo
    -0.08
    æĴŃæĬ¥
    -0.08
    CTS
    -0.08
    è´¢ç¨İ
    -0.08
    ä½ĵè´´
    -0.08
    POSITIVE LOGITS
    æľ¬åľ°
    0.11
    çĶŁäº§çļĦ
    0.10
    å°±è¿ij
    0.09
    çģĮ
    0.09
    èħ°
    0.09
    éĢĤ
    0.09
    mr
    0.09
    æĿİåħĪçĶŁ
    0.09
    วล
    0.09
    çİ«
    0.08
    Activations Density 0.051%

    No Known Activations