© 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. 6176
    Prev
    Next
    INDEX
    Explanations

    guess what

    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
    Negative Logits
    abble
    -0.10
    enton
    -0.10
    æIJŀ好
    -0.08
    æ·¡
    -0.08
    ä»ĭ
    -0.08
    梳
    -0.08
    详ç»Ĩä»ĭç»į
    -0.08
    æ·¡å®ļ
    -0.08
    oard
    -0.08
     Pais
    -0.08
    POSITIVE LOGITS
    çĮľ
    0.17
     Äijoán
    0.13
     guessed
    0.13
    çĮľæµĭ
    0.12
     guess
    0.12
    guess
    0.12
     guesses
    0.11
     predict
    0.11
     Guess
    0.10
    Guess
    0.10
    Activations Density 0.088%

    No Known Activations