© 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. 6095
    Prev
    Next
    INDEX
    Explanations

    cut out or sign up

    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
    æ·¡
    -0.09
    æ½ĩ
    -0.09
    cors
    -0.09
    ç´
    -0.09
    ç«ĭãģ¦
    -0.09
    åıįå¤į
    -0.09
    å¾ĢæĿ¥
    -0.09
    岸
    -0.09
    eration
    -0.08
    ä¸Ģå¾ĭ
    -0.08
    POSITIVE LOGITS
    åįģæĿ¡
    0.11
    éĢĤåIJĪèĩªå·±
    0.10
    isz
    0.09
    饱åĴĮ
    0.09
     volunteers
    0.09
    å¿ĹæĦ¿èĢħ
    0.08
    车çīĮ
    0.08
    иÑĤа
    0.08
    ordo
    0.08
    游æĪıçݩ家
    0.08
    Activations Density 0.073%

    No Known Activations