© 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. 32538
    Prev
    Next
    INDEX
    Explanations

    quick followed by a noun

    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
    åĮĸåIJĪ
    -0.11
     Ballard
    -0.10
    çĶļ
    -0.10
    TING
    -0.10
    çļĵ
    -0.10
    è®ļ
    -0.09
    ä¸ĢèĤ¡
    -0.09
    idis
    -0.09
    使ä¹ĭ
    -0.09
    opo
    -0.09
    POSITIVE LOGITS
    åĽ½æĥħ
    0.10
    .quick
    0.09
    enga
    0.09
    éĹ´éļĻ
    0.09
     quick
    0.09
    ilies
    0.08
    lest
    0.08
    ç®Ģ
    0.08
    ALS
    0.08
    çݯèĬĤ
    0.08
    Activations Density 0.039%

    No Known Activations