© 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. 5618
    Prev
    Next
    INDEX
    Explanations

    battery terminals

    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
    ä»ħä¾Ľ
    -0.10
    èŀ«
    -0.10
    .fd
    -0.10
    åŁİå¸ĤçļĦ
    -0.10
    ç¦ģ
    -0.09
    Versions
    -0.09
     Straw
    -0.09
    溽
    -0.09
    ä¸įéĢļ
    -0.09
    æĸ¯é¡¿
    -0.09
    POSITIVE LOGITS
    èĵĦçĶµæ±ł
    0.11
    æĭ¨
    0.10
    dorf
    0.09
    åħ¨èĩªåĬ¨
    0.09
    tridge
    0.08
    Adobe
    0.08
    iel
    0.08
     Lords
    0.08
     ITE
    0.08
    æł¡
    0.08
    Activations Density 0.068%

    No Known Activations