© 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. 59328
    Prev
    Next
    INDEX
    Explanations

    progress, development, career, journey

    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
    çļĦä¸ĢåĪĩ
    -0.09
    è´§
    -0.09
    Fal
    -0.09
    aklı
    -0.08
    çĤ¹å¤´
    -0.08
    plen
    -0.08
    壤
    -0.08
    ä¸īçĤ¹
    -0.08
    带åĪ°
    -0.08
    indow
    -0.08
    POSITIVE LOGITS
    çļĦ人çĶŁ
    0.12
    åıijå±ķåİĨç¨ĭ
    0.12
    人çĶŁçļĦ
    0.12
     ÑĢазвиÑĤиÑı
    0.12
    æ¼Ķåıĺ
    0.11
    æĹħç¨ĭ
    0.11
    å¾ģç¨ĭ
    0.11
     saga
    0.11
     journey
    0.11
    åİĨç¨ĭ
    0.10
    Activations Density 0.114%

    No Known Activations