© 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. 55725
    Prev
    Next
    INDEX
    Explanations

    storage, containing, recess, out

    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
    roker
    -0.10
     Cush
    -0.09
    æİ¢
    -0.09
    ivated
    -0.09
    訪
    -0.08
    .hot
    -0.08
     Hot
    -0.08
     Ale
    -0.08
    æ´»çĿĢ
    -0.08
    æľīçĶ¨
    -0.08
    POSITIVE LOGITS
    æĶ¶çº³
    0.13
    åį·
    0.12
    æĶ¶
    0.11
    åħ¥åºĵ
    0.11
    æĭ¿åĩºæĿ¥
    0.11
    æĶ¶åĽŀ
    0.11
     retract
    0.10
    å¼¼
    0.10
    æĭ¿æĿ¥
    0.10
    çĶ»åį·
    0.10
    Activations Density 0.132%

    No Known Activations