© 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. 61942
    Prev
    Next
    INDEX
    Explanations

    demonstrating or stating a fact

    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
    åĮĹ大
    -0.08
    doc
    -0.08
    æĶĺ
    -0.08
     permanent
    -0.07
    ä¸įæĺİçĻ½
    -0.07
    ierre
    -0.07
    åį³æŶ
    -0.07
     Kling
    -0.07
    xEB
    -0.07
    ä¸įåıªæĺ¯
    -0.07
    POSITIVE LOGITS
    ĥĿ
    0.10
    æѦåĬŁ
    0.09
    éĢĬ
    0.09
    ÐĽÐŀ
    0.09
    éĢĥ
    0.09
    好åĿı
    0.09
    .GO
    0.09
    åħīéĺ´
    0.08
    istically
    0.08
    aset
    0.08
    Activations Density 0.001%

    No Known Activations