© 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. 19129
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by new ideas

    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
    æīĵåIJ¬
    -0.09
    æĢª
    -0.09
    çļĦ主è¦ģ
    -0.08
    æİ£
    -0.08
    Monster
    -0.08
    çļĦåħ´è¶£
    -0.08
    ç¬ĭ
    -0.08
    çľĭ好
    -0.08
    è¿Ĥ
    -0.08
    纡
    -0.08
    POSITIVE LOGITS
    IPPING
    0.10
    æĦŁåĬ¨
    0.09
    å¢ĥçķĮ
    0.08
    éļ¾å¿ĺ
    0.08
    ocks
    0.08
    ä¹ĭæĥħ
    0.08
    ivot
    0.08
    icolon
    0.08
    ofday
    0.08
    áĥ¬
    0.08
    Activations Density 0.123%

    No Known Activations