© 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. 19231
    Prev
    Next
    INDEX
    Explanations

    NASA's current Hubble Space Telescope

    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
    ç«Ł
    -0.12
    æ¶īåıĬåĪ°
    -0.12
    è¿Ľåħ¥åĪ°
    -0.11
    为大家
    -0.10
    人们对
    -0.10
    åijĬè¯ī大家
    -0.10
    åľ¨éĩĮéĿ¢
    -0.10
    跻身
    -0.10
    è®°èĢħéĩĩ访
    -0.10
    è®°èĢħåľ¨
    -0.09
    POSITIVE LOGITS
    æīĭä¸Ń
    0.12
     via
    0.11
    ìĹIJê²Į
    0.10
    æīĭä¸Ĭ
    0.10
    æīĭéĩĮ
    0.09
    æīĭä¸ŃçļĦ
    0.09
    aru
    0.09
    åİ»äºĨ
    0.09
    çľ¼ä¸Ń
    0.09
    æĮĩå®ļ
    0.08
    Activations Density 0.196%

    No Known Activations