© 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. 1761
    Prev
    Next
    INDEX
    Explanations

    clothing and attire

    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
    èĬ±åĽŃ
    -0.09
    CES
    -0.09
     Fee
    -0.08
    çĦ¦æĢ¥
    -0.08
    è·³åĩº
    -0.08
    walls
    -0.08
    çĶ³
    -0.08
    åIJ±
    -0.08
     Walls
    -0.08
     fee
    -0.08
    POSITIVE LOGITS
    stile
    0.09
     phoenix
    0.09
    æıŃ示
    0.08
     Reve
    0.08
    caller
    0.08
    èµ°è·¯
    0.08
    èŁ¾
    0.08
    éĺ»åĬĽ
    0.08
    宽æĿ¾
    0.08
    æĢª
    0.08
    Activations Density 0.183%

    No Known Activations