© 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. 39814
    Prev
    Next
    INDEX
    Explanations

    statements about relationships and interactions

    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
    æİĴåĩº
    -0.09
    ellers
    -0.08
    Äĥm
    -0.08
    å®ĺåı¸
    -0.08
     unpopular
    -0.08
    æ¡Ī
    -0.08
    笨
    -0.08
    owners
    -0.08
    éķ¿å¯¿
    -0.08
     владелÑĮ
    -0.07
    POSITIVE LOGITS
    河边
    0.12
    æļ§æĺ§
    0.11
    深交
    0.11
    èģĮåĬ¡
    0.11
    æ´ģ
    0.11
    åIJĽåŃIJ
    0.11
    éĢĤ度
    0.10
    纯æ´ģ
    0.10
    æģĭæĥħ
    0.10
    èį¤
    0.10
    Activations Density 0.066%

    No Known Activations