© 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. 59092
    Prev
    Next
    INDEX
    Explanations

    related, linked, together

    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
    éĿ¢åīį
    -0.09
    à¸ģา
    -0.09
    åIJĮ缣
    -0.08
    eor
    -0.08
    dden
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    stral
    -0.08
    jet
    -0.08
    lya
    -0.08
    /commons
    -0.08
    POSITIVE LOGITS
    åıĮåıĮ
    0.15
    åľ¨ä¸Ģèµ·
    0.12
    è¿Ļ两个
    0.11
    è¿Ļ两
    0.10
     together
    0.10
    两èĢħ
    0.10
    äºĮèĢħ
    0.10
    åīįèĢħ
    0.10
     themselves
    0.09
    å¾Īéķ¿
    0.09
    Activations Density 0.212%

    No Known Activations