© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new sentence

    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
    èħĬ
    -0.09
    åįĴ
    -0.08
    lope
    -0.08
    æıIJè´¨
    -0.08
    acie
    -0.08
    udas
    -0.08
    ä¸įéĢļ
    -0.08
    濯
    -0.08
    éĻĦåĬłåĢ¼
    -0.08
    帮æī¶
    -0.08
    POSITIVE LOGITS
    è·¨
    0.11
    æ¿Ģ
    0.10
    ä¸ĢæĹı
    0.10
    ä¸ĢåŃĹ
    0.09
    æĤ²è§Ĥ
    0.09
    好象
    0.09
    ä¸ŃåĽ½æĸĩåĮĸ
    0.09
    æĤ²åĵĢ
    0.09
    èŃ
    0.09
    æīĢå±ŀ
    0.09
    Activations Density 0.005%

    No Known Activations