© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    titles followed by colons

    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
    å°½æĹ©
    -0.10
    éļ¾æĢª
    -0.09
    åĪ°åºķæĺ¯
    -0.09
    æľĪåºķ
    -0.09
    ivar
    -0.08
    æĸ°åħ´äº§ä¸ļ
    -0.08
    åIJĮä¸Ģ个
    -0.08
    尽快
    -0.08
    åĪ°æŶåĢĻ
    -0.08
    åİŁæľ¬
    -0.08
    POSITIVE LOGITS
    åĨį次
    0.12
    æĽ´åĬł
    0.10
    éĩijèŀįåį±æľº
    0.10
    缴åĪ°
    0.10
    è¿Ľä¸ĢæŃ¥
    0.10
    .useState
    0.10
    èĩ³ä»Ĭ
    0.10
    汶å·Ŀ
    0.09
    ãģķãĤīãģ«
    0.09
     Beginning
    0.09
    Activations Density 0.289%

    No Known Activations