© 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. 633
    Prev
    Next
    INDEX
    Explanations

    "whoever believes" or "who gives"

    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¸Ģéĥ¨åĪĨ
    -0.10
    å¤ĩæ¡Ī
    -0.10
    çļĦåħ³éĶ®
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
    åIJİåĨį
    -0.09
    çŀ
    -0.09
    çĪº
    -0.09
    âĨĻ
    -0.09
    çļĦåľ°ä½į
    -0.09
    ç¼ij
    -0.09
    POSITIVE LOGITS
    hana
    0.10
    _aa
    0.09
    åĸľ
    0.08
    æĪij以为
    0.08
    .getConfig
    0.08
    ä¼Łå¤§çļĦ
    0.08
    èĩ³äºİ
    0.07
    两ä¸ī
    0.07
    .getBounds
    0.07
    EMPLARY
    0.07
    Activations Density 0.242%

    No Known Activations