© 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. 17273
    Prev
    Next
    INDEX
    Explanations

    in a/the phrase

    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
    emo
    -0.08
    çľĭä¸Ĭåİ»
    -0.08
    hud
    -0.08
     cheer
    -0.08
    2
    -0.08
    çļĦç¼ĺæķħ
    -0.08
     lei
    -0.07
    uke
    -0.07
    á»ĥ
    -0.07
    Extent
    -0.07
    POSITIVE LOGITS
    çłĶ究æĬ¥åijĬ
    0.11
    å¸Ĥåľºä¸Ĭ
    0.10
    æ¶ĪåĮĸ
    0.10
    ä¸į论
    0.09
    è¡Ĺä¸Ĭ
    0.09
    å¼Ĭ端
    0.09
    ä»Ģä¹Īåij¢
    0.09
    æIJĤ
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    å¸ĥæľĹ
    0.09
    Activations Density 0.172%

    No Known Activations