© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    also known as

    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¸Ģæ³¢
    -0.09
    kit
    -0.09
    èĩ³æѤ
    -0.09
    好åIJĥ
    -0.09
    ä¸įæĩĤ
    -0.08
    bet
    -0.08
    ä¹Łåıªæľī
    -0.08
    æīĭä¸ĭ
    -0.08
    é¹ħ
    -0.08
    ossier
    -0.08
    POSITIVE LOGITS
    å¾Īå¤ļäºĭæĥħ
    0.10
    aux
    0.09
    GAN
    0.09
    åĽłä¸ºåľ¨
    0.09
    æľīçļĦ
    0.09
     biá»ĩt
    0.09
    æĺ¯ä¸Ģéĥ¨
    0.09
    sometimes
    0.09
     sometimes
    0.09
    ifice
    0.08
    Activations Density 0.074%

    No Known Activations