© 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. 11960
    Prev
    Next
    INDEX
    Explanations

    good reasons why

    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
    è¿Ļæĺ¯åĽłä¸º
    -0.13
    å°±æĺ¯åĽłä¸º
    -0.11
    æĺ¯åĽłä¸º
    -0.11
    åĽłä¸ºå¥¹
    -0.11
    çļĦç¡®æĺ¯
    -0.10
    ç¡®å®ŀæĺ¯
    -0.10
    å±ŀå®ŀ
    -0.10
    æ¯ķç«Ł
    -0.10
    LOPT
    -0.09
     Wise
    -0.09
    POSITIVE LOGITS
    8
    0.10
    7
    0.09
     eBook
    0.09
    å°Ĩåħ¶
    0.09
    6
    0.09
    ç§ĺ
    0.09
    9
    0.08
    5
    0.08
    etwork
    0.08
    4
    0.08
    Activations Density 0.003%

    No Known Activations