© 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. 56967
    Prev
    Next
    INDEX
    Explanations

    male names

    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
    éķĿ
    -0.10
    çĻ½æ²Ļ
    -0.09
    atum
    -0.09
    oreach
    -0.09
    åºĬä¸Ĭ
    -0.09
    å¾ĹäºĨ
    -0.09
     onHide
    -0.08
    (*)(
    -0.08
    为ä»Ģä¹Īä¼ļ
    -0.08
    ÙĬØ«
    -0.08
    POSITIVE LOGITS
    pson
    0.09
    sson
    0.09
    绵
    0.09
    çļĦæĥħæĦŁ
    0.09
    fulness
    0.09
    ëĭ¹
    0.09
    âĸ¾
    0.08
    çļĦæĥħ
    0.08
    æĬ¬
    0.08
    èĵŁ
    0.08
    Activations Density 0.252%

    No Known Activations