© 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. 31796
    Prev
    Next
    INDEX
    Explanations

    combination, joint, common, together

    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
    ä¸İä¼Ĺä¸įåIJĮ
    -0.12
    ä¸İåħ¶ä»ĸ
    -0.10
    夫å¦ĩ
    -0.10
    线ä¸Ĭ线ä¸ĭ
    -0.10
    æĺ¯éĿŀ
    -0.09
    idge
    -0.09
    们éĥ½
    -0.09
    ä¸İæѤ
    -0.09
    åĽĽå¤Ħ
    -0.09
    å¤ļ人
    -0.09
    POSITIVE LOGITS
    CN
    0.08
    DataStream
    0.08
    绿èī²éĢļéģĵ
    0.08
    åľ¨åIJĮä¸Ģ
    0.08
     CN
    0.08
    reau
    0.08
    าà¸ĩ
    0.07
    .cp
    0.07
    еÑģ
    0.07
    rell
    0.07
    Activations Density 0.522%

    No Known Activations