© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    leave or departure

    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
    ì±Ħ
    -0.09
    åħī线
    -0.08
    åħľ
    -0.08
    ç´¯
    -0.08
     sup
    -0.08
    èµ°å¾Ĺ
    -0.08
    表彰
    -0.08
    lage
    -0.08
    轩
    -0.08
    æ³īæ°´
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľå²Ĺä½į
    0.11
    è¿ĻåĿĹ
    0.10
    LocalizedString
    0.10
    客æłĪ
    0.09
    æ·±å¤Ħ
    0.09
    座ä½į
    0.09
    å¸Ń
    0.09
    æĢĢæĬ±
    0.09
    bern
    0.09
    itre
    0.09
    Activations Density 0.037%

    No Known Activations