© 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. 49344
    Prev
    Next
    INDEX
    Explanations

    feminazi

    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
    lingen
    -0.09
    ä¸Ģç«Ļ
    -0.08
    è½
    -0.08
    _consts
    -0.08
    以人为
    -0.08
    åĮ»ç§ij
    -0.08
    ãĤ¿ãĥ«
    -0.08
    uzu
    -0.08
    漫
    -0.08
    è¾ĸ
    -0.08
    POSITIVE LOGITS
    é¢ijéģĵ
    0.08
    çijĻ
    0.08
    äºĭåĦ¿
    0.08
    ç²¾èĭ±
    0.08
     Flake
    0.08
    å¹´ä¹ĭ
    0.07
    èĦ
    0.07
    泯
    0.07
    leader
    0.07
    åĢĴ
    0.07
    Activations Density 0.170%

    No Known Activations