© 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. 49411
    Prev
    Next
    INDEX
    Explanations

    distributed under license

    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
    ä¹ĭæŶ
    -0.09
    jac
    -0.08
     зай
    -0.08
    楼æĪ¿
    -0.08
    è¿ĺè®°å¾Ĺ
    -0.08
    åĪ°æĿ¥
    -0.08
    éĥľ
    -0.08
    çIJļ
    -0.08
    为ä»Ģä¹Īä¸į
    -0.08
     richest
    -0.08
    POSITIVE LOGITS
    éķ°
    0.09
    ienza
    0.08
    cott
    0.08
    读åIJİ
    0.08
    çĬ¯
    0.08
    æ´¸
    0.08
    å§ij
    0.08
    alık
    0.08
     Unary
    0.08
    frame
    0.08
    Activations Density 1.505%

    No Known Activations