© 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. 61181
    Prev
    Next
    INDEX
    Explanations

    extract, heat, cups

    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
    å¹²æ¶ī
    -0.10
    åŃŁ
    -0.10
    INAL
    -0.10
    éĿ¢æĿ¡
    -0.10
    äºĶå®ĺ
    -0.10
    еÑģп
    -0.09
    ä»ĵ
    -0.09
    çĶ»åį·
    -0.09
    ären
    -0.09
    вÑĢеменно
    -0.09
    POSITIVE LOGITS
    ä¸įå®ľ
    0.09
    ä¸įåı¯ä»¥
    0.08
    ex
    0.08
    amus
    0.08
     seal
    0.08
    åģļæ³ķ
    0.08
    extract
    0.08
     ast
    0.08
    bru
    0.08
    è¯ķè¯ķ
    0.07
    Activations Density 0.028%

    No Known Activations