© 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. 24298
    Prev
    Next
    INDEX
    Explanations

    such conditions, scars, or structures

    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
    éĨª
    -0.10
    -video
    -0.09
    ä¼ij
    -0.09
    estar
    -0.09
    å®ĥæĺ¯
    -0.08
    WithOptions
    -0.08
    ÑĶ
    -0.08
    пиÑģ
    -0.08
    beit
    -0.07
    mk
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.12
     wÅĤaÅĽnie
    0.10
    æīĢ以说
    0.10
    ä¸Ĭè¿°
    0.10
    è¿Ļä¸ĢåĪĩ
    0.09
    è¿ĻäºĽ
    0.09
    çijŁ
    0.09
    建çŃijä¸ļ
    0.09
    åīįèĢħ
    0.09
    loyd
    0.09
    Activations Density 0.388%

    No Known Activations