© 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. 18660
    Prev
    Next
    INDEX
    Explanations

    ATI CCC or patient conversion

    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
    躯
    -0.10
     OT
    -0.09
    STD
    -0.09
     ot
    -0.09
    gross
    -0.09
    èĭ´
    -0.09
    çĽ´è¾¾
    -0.09
    æ²½
    -0.09
    èĶĹ
    -0.08
    åĺ»åĺ»
    -0.08
    POSITIVE LOGITS
    기ê°Ģ
    0.09
    irc
    0.08
    lop
    0.08
    è¿Ļæł·çļĦ
    0.08
    å·´
    0.08
    ç¿»
    0.08
    主æµģ
    0.08
    çıĬçijļ
    0.08
    ä¸ĢåŃĹ
    0.08
    产åĵģçļĦ
    0.08
    Activations Density 0.019%

    No Known Activations