© 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. 39822
    Prev
    Next
    INDEX
    Explanations

    outfits and accessory styles

    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
    å¤ĩçĶ¨
    -0.12
    çĺ¾
    -0.09
    zers
    -0.08
    åIJĦé¡¹å·¥ä½ľ
    -0.08
    éĵĸ
    -0.08
    Jam
    -0.08
    yan
    -0.08
    åľ»
    -0.08
    欢
    -0.08
     laying
    -0.08
    POSITIVE LOGITS
    å·½
    0.10
    sol
    0.10
    ç¦ıéŁ³
    0.09
    çĵ¶é¢Ī
    0.09
    æķĻä½ł
    0.09
     пÑĢоб
    0.09
    èĩĬ
    0.08
    ashi
    0.08
    驾é©Ń
    0.08
    秾
    0.08
    Activations Density 0.043%

    No Known Activations