© 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. 26354
    Prev
    Next
    INDEX
    Explanations

    now!

    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
    æѤåīį
    -0.11
    å½ĵæŶ
    -0.10
    æĪijå½ĵæŶ
    -0.10
    çİ°åľ¨å¾Īå¤ļ
    -0.10
    çķ¶æĻĤ
    -0.09
    æŃ¤æ¬¡
    -0.09
    uely
    -0.09
    .googlecode
    -0.09
    è¿Ļä¹Ī说
    -0.09
    æľ¬è½®
    -0.08
    POSITIVE LOGITS
    adays
    0.21
    here
    0.14
    abouts
    0.13
    aday
    0.12
    ski
    0.12
    days
    0.11
    ledge
    0.11
    HERE
    0.11
    casting
    0.10
    为æŃ¢
    0.10
    Activations Density 0.082%

    No Known Activations