© 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. 57875
    Prev
    Next
    INDEX
    Explanations

    in a/the

    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
    å¼Ĥ
    -0.10
     Arch
    -0.09
    emade
    -0.09
    æī³
    -0.09
    ewear
    -0.09
    æĪij家
    -0.09
    orical
    -0.09
    ysz
    -0.09
    大大
    -0.09
    liga
    -0.09
    POSITIVE LOGITS
    æĺ¯ä¸Ģ件
    0.10
    åIJĦ个çݯèĬĤ
    0.10
    ä¸Ģ件äºĭæĥħ
    0.09
    ä¸Ģå¹ħ
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    çļĦ空éĹ´
    0.08
    çĵ
    0.08
    ä»ĬåIJİ
    0.08
    ä¸Ńç§ĭ
    0.08
    æľīä¸Ģå®ļçļĦ
    0.08
    Activations Density 0.501%

    No Known Activations