© 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. 5621
    Prev
    Next
    INDEX
    Explanations

    place names after 'from' or 'of'

    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
    ä¸İä¸ŃåĽ½
    -0.09
    æĪij以为
    -0.08
    ä¸ĢéĹ´
    -0.08
    åĸĪ
    -0.08
    mgr
    -0.08
    ä¸Ģ段
    -0.08
     Ñħа
    -0.08
    ä¸ĢåIJį
    -0.08
     tah
    -0.08
    ä¸Ģçīĩ
    -0.08
    POSITIVE LOGITS
    çļĦçIJĨçĶ±
    0.10
    avez
    0.09
    çļĦæĦ¿æľĽ
    0.09
    çļĦ身影
    0.09
    routes
    0.08
    åIJĮåŁİ
    0.08
    çļĦä¼Łå¤§
    0.08
    è·³è·ĥ
    0.08
    sse
    0.08
    _atom
    0.08
    Activations Density 0.032%

    No Known Activations