© 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. 34565
    Prev
    Next
    INDEX
    Explanations

    much of [noun]

    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
    çļĦ身影
    -0.09
    ä¸Ģçīĩ
    -0.09
    å°½éĩı
    -0.09
    ä¸Ģç¬ij
    -0.09
    ä¸Ģ群
    -0.09
    çļĦæŃ¥ä¼IJ
    -0.09
    ä½ķæŶ
    -0.09
    OMIC
    -0.09
    çļĦåIJĪä½ľ
    -0.08
    è¾ĥå·®
    -0.08
    POSITIVE LOGITS
    pra
    0.10
    orate
    0.10
    积èĵĦ
    0.10
    æĸĩåĮĸåĴĮ
    0.10
    å½»
    0.09
    caff
    0.09
    mah
    0.09
    pute
    0.09
     controversy
    0.09
    å®īä¿Ŀ
    0.09
    Activations Density 0.053%

    No Known Activations