© 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. 24204
    Prev
    Next
    INDEX
    Explanations

    and | conjunction

    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
    è¦ģä¹Ī
    -0.12
    çĶļèĩ³
    -0.12
    çĶļèĩ³æĺ¯
    -0.12
     tháºŃm
    -0.11
    çī¹åĪ«æĺ¯
    -0.10
    ä¹ĥèĩ³
    -0.10
    å°¤åħ¶æĺ¯
    -0.10
    çĶļèĩ³è¿ĺ
    -0.10
    æ±°
    -0.10
    寡
    -0.09
    POSITIVE LOGITS
     ÙĩÙĨاÙĥ
    0.09
    /OR
    0.09
     ÑģÑĤоиÑĤ
    0.09
    excerpt
    0.09
    naments
    0.08
    nette
    0.08
    å¤Ħå¤Ħéķ¿
    0.08
    achts
    0.08
    биÑĢ
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    Activations Density 0.032%

    No Known Activations