© 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. 12169
    Prev
    Next
    INDEX
    Explanations

    I can have my

    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
     yourself
    -0.11
    æĪij们认为
    -0.10
    scape
    -0.09
    ping
    -0.09
    ç»Ļ大家
    -0.09
    å°ıç¼ĸ
    -0.09
    ç¬ĶèĢħ
    -0.09
    eral
    -0.08
    ç¼
    -0.08
    ä¾Ľå¤§å®¶
    -0.08
    POSITIVE LOGITS
    åı«æĪij
    0.16
    æĪijåı¯ä»¥
    0.14
    æĺ¯æĪijçļĦ
    0.13
    åľ¨æĪijçļĦ
    0.13
    åĽłä¸ºæĪij
    0.13
    è·ŁæĪij
    0.12
    äºİæĺ¯æĪij
    0.12
    éĹ®æĪij
    0.11
    åijĬè¯īæĪij
    0.11
    使æĪij
    0.11
    Activations Density 0.246%

    No Known Activations