© 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. 55335
    Prev
    Next
    INDEX
    Explanations

    with other entities

    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
    åģļå¾Ĺ
    -0.12
    åģļä¸ĢäºĽ
    -0.10
     ÐĴладим
    -0.10
    éĥ½æĥ³
    -0.10
    ç¼Ķ
    -0.10
    èī°éļ¾
    -0.09
    äºĭå®ľ
    -0.09
    åľ¨çº¿åĴ¨è¯¢
    -0.09
    Æ¡i
    -0.09
    Carthy
    -0.09
    POSITIVE LOGITS
    尾巴
    0.09
    æĪĸèĢħ说
    0.08
    Ĥ¬
    0.08
    绳
    0.07
    timer
    0.07
    ãĥªãĥ³ãĤ°
    0.07
    IQ
    0.07
    æķħ
    0.07
    çļĦä¸Ģç§į
    0.07
    æĪĸå°Ĩ
    0.07
    Activations Density 0.073%

    No Known Activations