© 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. 61246
    Prev
    Next
    INDEX
    Explanations

    legal or financial future

    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
    ä½Ĩæĺ¯ä»ĸ
    -0.09
    ÂŃ
    -0.08
    —
    -0.08
    ãĢĵ
    -0.08
    æıIJä¾Ľä¼ĺè´¨
    -0.08
    æŁĵ
    -0.08
    elder
    -0.07
    å½ĵåľº
    -0.07
    æ»´
    -0.07
    \↵
    -0.07
    POSITIVE LOGITS
    ĥĿ
    0.09
    æŃ
    0.09
    RICS
    0.09
    èĥ¸åīį
    0.08
    APH
    0.08
    газ
    0.08
    åĨħå¹ķ
    0.08
    yny
    0.08
    EMPLARY
    0.08
    (...)↵
    0.08
    Activations Density 4.924%

    No Known Activations