© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 953
    Prev
    Next
    INDEX
    Explanations

    understanding, knowing, guessing

    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
    èĸª
    -0.09
    æį»
    -0.08
    æĴŃ
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    Kill
    -0.08
     Staff
    -0.08
    çĸ¾
    -0.08
     Kill
    -0.07
    ç´łæĿIJ
    -0.07
    \Base
    -0.07
    POSITIVE LOGITS
    é»ĺå¥ij
    0.15
    æı£
    0.14
    åīįçŀ»
    0.14
    æĦŁåºĶ
    0.13
    人å¿ĥ
    0.11
     Äijoán
    0.11
    æĩĤäºĭ
    0.11
    å¯Ł
    0.10
    æ´ŀå¯Ł
    0.10
    åīįçŀ»æĢ§
    0.10
    Activations Density 0.051%

    No Known Activations