© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    points, marks, score, champs, plus

    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
    ald
    -0.08
    çĸ¾
    -0.08
    ness
    -0.08
    yle
    -0.08
    alth
    -0.08
    ä¾Ŀæīĺ
    -0.08
    æĿ
    -0.08
     Gord
    -0.08
    -validation
    -0.07
     Rockefeller
    -0.07
    POSITIVE LOGITS
    åĬłåĪĨ
    0.09
    åķľ
    0.09
    ä¿¡æģ¯åıijå¸ĥ
    0.09
    毫ä¸įçĬ¹è±«
    0.09
    æĭįæĭį
    0.09
    人æĢ§
    0.09
    赢家
    0.09
    æ®Ĩ
    0.09
    ä¸ĩæĪ·
    0.09
    èĥľåĪ©
    0.08
    Activations Density 0.025%

    No Known Activations