© 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. 17829
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

    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
     ngh
    -0.09
    è§Ĩ线
    -0.08
    wig
    -0.08
    èµĦ讯
    -0.08
    éĢĥ离
    -0.08
    æĪĺèĥľ
    -0.08
    ays
    -0.08
    iku
    -0.08
     Zig
    -0.08
    çĤ®
    -0.08
    POSITIVE LOGITS
    æĪijæīį
    0.09
     Hond
    0.09
    (SQL
    0.09
    ascade
    0.08
    èĶ¬
    0.08
    Cit
    0.08
    æīĢèĥ½
    0.08
    nton
    0.08
     conting
    0.08
    éĵ¤
    0.08
    Activations Density 0.022%

    No Known Activations