© 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. 6374
    Prev
    Next
    INDEX
    Explanations

    .pdf file names

    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
    /cgi
    -0.09
    ilk
    -0.08
    ä¼łéĹ»
    -0.08
    .createComponent
    -0.08
    èĸª
    -0.08
     Arg
    -0.07
    youtube
    -0.07
    atoire
    -0.07
    ä¹ĭä½ľ
    -0.07
    виÑĤ
    -0.07
    POSITIVE LOGITS
    åIJįåĪĹ
    0.11
    童年
    0.10
    æŶæĬ¥
    0.10
    ç»Ļ人
    0.10
    igue
    0.10
    åIJij社ä¼ļ
    0.09
    èĢĮåİ»
    0.09
    æ±ĤèģĮ
    0.09
    绪
    0.09
    çļĦ好å¤Ħ
    0.09
    Activations Density 0.075%

    No Known Activations