© 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. 33353
    Prev
    Next
    INDEX
    Explanations

    Yahoo Inc. Holdings declined Fantasy News

    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
    æĦıæĢĿ
    -0.10
    éĿ©
    -0.10
    âĢ¢↵↵
    -0.08
    ÑĥÑĪки
    -0.08
    å½ĵéĢī
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
    çĿĢä»ĸ
    -0.08
    人为
    -0.08
    æĿ¥èĩª
    -0.08
    ä¾Ĩèĩª
    -0.08
    POSITIVE LOGITS
    inated
    0.09
    beeld
    0.09
    ying
    0.09
    annes
    0.09
    onica
    0.09
    lag
    0.09
    pon
    0.09
    åħ¨èº«
    0.09
    åı¯è§Ĥ
    0.08
    æĤĸ
    0.08
    Activations Density 0.011%

    No Known Activations