© 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. 16619
    Prev
    Next
    INDEX
    Explanations

    found in texts discussing directions or guidelines

    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
    åĥ»
    -0.10
    èµģ
    -0.09
    ple
    -0.09
    å§ĵåIJį
    -0.09
    hope
    -0.09
    cape
    -0.09
    å¿ĥè¡Ģ
    -0.08
    .bb
    -0.08
     kaz
    -0.08
    éĹª
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.13
    åį´æĺ¯
    0.12
    åıįèĢĮ
    0.12
    åį»
    0.11
    åį´
    0.10
    åį´åıĪ
    0.10
     BUT
    0.10
    è¿ĺä¸įå¦Ĥ
    0.10
    ä½Ĩæĺ¯æĪij
    0.10
    åıįåĢĴ
    0.10
    Activations Density 2.460%

    No Known Activations