© 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. 54423
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    æ¯Ľ
    -0.10
    cro
    -0.09
    èijŃ
    -0.08
    Delegate
    -0.08
     Prev
    -0.08
    itim
    -0.08
    åłª
    -0.08
    äºĭåħĪ
    -0.08
    uka
    -0.08
    ander
    -0.08
    POSITIVE LOGITS
    aos
    0.10
    æĤ¬
    0.10
    æĤ©
    0.10
    èķĪ
    0.09
    ç»ĵæĿŁ
    0.09
    Åĭ
    0.08
    ç«£
    0.08
    漫éķ¿çļĦ
    0.08
    redux
    0.08
    åĪĹ为
    0.08
    Activations Density 0.179%

    No Known Activations