© 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. 53763
    Prev
    Next
    INDEX
    Explanations

    X words

    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
    uta
    -0.09
    .deb
    -0.08
    ugging
    -0.08
    æĹłçº¿çĶµ
    -0.08
    (EIF
    -0.08
    mares
    -0.08
     Affero
    -0.08
    alse
    -0.08
    dle
    -0.08
    械
    -0.08
    POSITIVE LOGITS
    ä¸ĩæĪ·
    0.09
    frog
    0.09
    çļĦçľĭæ³ķ
    0.09
    æ¡ī
    0.09
    ä¸Ĭä¸ĭ
    0.08
    RenderWindow
    0.08
    ви
    0.08
    ç®Ĺæĺ¯
    0.08
    çľĭæ³ķ
    0.08
    æ´Ļ
    0.08
    Activations Density 0.045%

    No Known Activations