© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    leaves changing colors in autumn

    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
    çģ¯çģ«
    -0.11
    man
    -0.09
    çī¢
    -0.09
    æģģ
    -0.09
    æī¦
    -0.09
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.09
    è¾ĺ
    -0.09
    .Clock
    -0.08
    rand
    -0.08
    åĬª
    -0.08
    POSITIVE LOGITS
    èIJ½åı¶
    0.13
    ç§ĭ
    0.12
    ç§ĭåĨ¬
    0.12
    æŀ«
    0.11
    ç§ĭ天
    0.11
    åĩĮ
    0.11
    ç§ĭåŃ£
    0.11
    åĺĺ
    0.10
     autumn
    0.10
     Fall
    0.10
    Activations Density 0.044%

    No Known Activations