© 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. 50123
    Prev
    Next
    INDEX
    Explanations

    biopsy and autopsy

    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
    çļĦæĥħ
    -0.10
     Perr
    -0.09
    uster
    -0.08
    upert
    -0.08
    ä¸ĢæľŁ
    -0.08
    azen
    -0.08
    archy
    -0.08
    ules
    -0.08
    ä¸ĢéĿ¢
    -0.08
    ä¸Ģæīĭ
    -0.08
    POSITIVE LOGITS
    rooms
    0.10
    è¿ĩçļĦ
    0.10
    大楼
    0.10
    æ³¼
    0.09
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    agic
    0.09
    秦çļĩ
    0.09
    REE
    0.09
    ç¦ı彩
    0.09
    éľĢæ±Ĥ
    0.09
    Activations Density 0.021%

    No Known Activations