© 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. 57399
    Prev
    Next
    INDEX
    Explanations

    soft drinks and beverages

    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
    iden
    -0.09
    ç¡IJ
    -0.09
    æĸ°æĹ¶æľŁ
    -0.09
    èĬ±æľµ
    -0.08
    вид
    -0.08
    åĿ¨
    -0.08
     dut
    -0.08
    çĦķ
    -0.08
    åľ£åľ°
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    POSITIVE LOGITS
    AccessException
    0.11
    ä¸įä¸Ĭ
    0.09
     Mell
    0.09
    riages
    0.08
    INGTON
    0.08
    merce
    0.08
    ä¸ĢåIJį
    0.08
    GINE
    0.08
    ockets
    0.08
    ãģĴ
    0.08
    Activations Density 0.009%

    No Known Activations