© 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. 6127
    Prev
    Next
    INDEX
    Explanations

    marine organisms and life

    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
    orris
    -0.10
    æĶ¶è´Ń
    -0.09
    åĨ²åĬ¨
    -0.09
    æĥľ
    -0.08
    çĺ¾
    -0.08
    olen
    -0.08
    çĥ¯
    -0.08
    åĬĿ
    -0.08
    ettings
    -0.08
    orz
    -0.08
    POSITIVE LOGITS
     мн
    0.09
    ç¡®ç«ĭ
    0.08
     Dice
    0.08
     ìī½ê²Į
    0.08
    ellow
    0.08
    inc
    0.08
    бÑĢ
    0.08
    æĸ°æĿIJæĸĻ
    0.08
    æ·±å±Ĥ
    0.08
    æ³ł
    0.08
    Activations Density 0.136%

    No Known Activations