© 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. 31791
    Prev
    Next
    INDEX
    Explanations

    hack, ice cream, Christmas, healthcare, festivals, virtualized, chef, Woods

    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
     полÑĥ
    -0.09
    ä¸ĢæµģçļĦ
    -0.09
    æ¹ĸ
    -0.09
    精彩çļĦ
    -0.08
    åIJĥå¾Ĺ
    -0.08
    ched
    -0.08
    èī°
    -0.08
    çŀĦåĩĨ
    -0.08
    åŃº
    -0.08
    éĢ®
    -0.08
    POSITIVE LOGITS
    è¿Ŀæ³ķ
    0.09
    æķıæĦŁ
    0.09
    alls
    0.08
    æľªç»ıæİĪæĿĥ
    0.08
    å®īåħ¨
    0.08
    atory
    0.08
    wor
    0.08
    æĹłè¾ľ
    0.08
    liv
    0.08
    ä¸įæħİ
    0.08
    Activations Density 0.968%

    No Known Activations