© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38205
    Prev
    Next
    INDEX
    Explanations

    onto, upon, on words

    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
    åľ¨å¤ĸ
    -0.10
    INES
    -0.09
    æĬĬ她
    -0.09
    让她
    -0.09
    æĮ½åĽŀ
    -0.09
    bridge
    -0.08
    åĶ®
    -0.08
    uden
    -0.08
    让å®ĥ
    -0.08
    .getList
    -0.08
    POSITIVE LOGITS
    éĢ¼è¿ij
    0.12
    UND
    0.10
    mith
    0.09
    ç¾Ĭæ¯Ľ
    0.09
    rys
    0.09
     onto
    0.09
    åĨł
    0.09
    ä¼ļ对
    0.09
    jay
    0.08
    ä¸ĢåĽ¢
    0.08
    Activations Density 0.051%

    No Known Activations