© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62980
    Prev
    Next
    INDEX
    Explanations

    coming soon

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çı©
    -0.09
    è¹´
    -0.09
    éĶµ
    -0.09
    åĬ£
    -0.09
    è®®äºĭ
    -0.08
    åģļäºĭ
    -0.08
    人æĿĥ
    -0.08
    lest
    -0.08
    绯
    -0.08
    cess
    -0.08
    POSITIVE LOGITS
    LAN
    0.10
    äºijéĽĨ
    0.10
    çļĦæĹ¥åŃIJéĩĮ
    0.10
    arring
    0.10
    aned
    0.09
    åĩłå¼ł
    0.09
    zik
    0.09
    ä¸įçŁ¥ä¸įè§ī
    0.09
    ész
    0.09
     Ez
    0.09
    Activations Density 0.029%

    No Known Activations