© 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. 26633
    Prev
    Next
    INDEX
    Explanations

    Audi, Volkswagen, Polo

    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
    nl
    -0.10
    åĸĺ
    -0.09
     Moz
    -0.09
    entropy
    -0.09
    å®Ŀå®ī
    -0.09
    æĥº
    -0.09
    éĹºèľľ
    -0.09
    ä¹Ŀ大
    -0.08
    è´¨åľ°
    -0.08
    åĪĨæķ£
    -0.08
    POSITIVE LOGITS
    æĮĩ
    0.09
    loo
    0.09
    ä¸İä¼Ĺä¸įåIJĮ
    0.08
    模åĿĹ
    0.08
    Nib
    0.08
     decltype
    0.08
    ç¡®
    0.08
    âĵĴ
    0.08
    å¾¼
    0.08
    boro
    0.08
    Activations Density 0.040%

    No Known Activations