© 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. 22403
    Prev
    Next
    INDEX
    Explanations

    may be

    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
    æīĢè°ĵ
    -0.10
    ä¸ĢåįĬ
    -0.10
    æĪª
    -0.10
    çĭ¬
    -0.09
    üs
    -0.09
    è´Łæĭħ
    -0.08
    å¤ļä½ĻçļĦ
    -0.08
    æīĢè°ĵçļĦ
    -0.08
    çĽ¸ä¿¡
    -0.08
     ÑģÑĤало
    -0.08
    POSITIVE LOGITS
    ä¼ļæľī
    0.11
    åľ¨æľªæĿ¥
    0.10
    endet
    0.10
    æľªæĿ¥
    0.10
    eti
    0.09
    stellen
    0.09
    åģ¶
    0.09
     Codec
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    ledge
    0.09
    Activations Density 0.083%

    No Known Activations