© 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. 50779
    Prev
    Next
    INDEX
    Explanations

    look like

    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¸ĢåıĮ
    -0.11
    åĬŀå®ŀäºĭ
    -0.10
    ockey
    -0.10
    åĽŀäºĭ
    -0.10
    åĬłçĽŁ
    -0.10
    çŃĶåį·
    -0.10
    åĥı个
    -0.09
    LIKELY
    -0.09
    ä¸ŃåĮ»
    -0.09
    æĬ¤çħ§
    -0.09
    POSITIVE LOGITS
    ãĤ¤ãĥ«
    0.09
    èįīåİŁ
    0.09
    xis
    0.09
    Bat
    0.09
    bat
    0.09
    飫
    0.09
    ä¿¡è´·
    0.09
    èĬ¥
    0.09
    èĿĻ
    0.08
    èĽ¾
    0.08
    Activations Density 0.096%

    No Known Activations