© 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. 19303
    Prev
    Next
    INDEX
    Explanations

    self-pollination or seed dispersal

    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
     vit
    -0.10
    è·¡
    -0.09
    çĴŁ
    -0.09
    iren
    -0.09
    èĤ¯
    -0.09
    endas
    -0.08
    å·¥ä½ľæķĪçİĩ
    -0.08
    ç´§å¼ł
    -0.08
    éĻªçĿĢ
    -0.08
    人åĬĽ
    -0.08
    POSITIVE LOGITS
    å°ĺ
    0.09
    çģ°å°ĺ
    0.09
    isch
    0.09
    塵
    0.09
    åĶ±
    0.09
    æĹ¶è¾°
    0.09
    æķ£å¸ĥ
    0.09
    éªŀ
    0.09
    ç±½
    0.09
     diffuse
    0.09
    Activations Density 0.073%

    No Known Activations