© 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. 23839
    Prev
    Next
    INDEX
    Explanations

    towns, counties, or municipalities

    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
    秦çļĩå²Ľ
    -0.09
    éķ¿åŁİ
    -0.09
    èĦĸ
    -0.09
    unbind
    -0.09
    Castle
    -0.09
    èĩĨ
    -0.08
    楯
    -0.08
    asonry
    -0.08
    éĢĸ
    -0.08
    è²Ĥ
    -0.08
    POSITIVE LOGITS
    èľĴ
    0.11
    èĥ°
    0.10
    éĵ¶å·Ŀ
    0.09
    èį¥
    0.09
    Liverpool
    0.09
    ç²½åŃIJ
    0.09
    æµĶ
    0.09
    æµ·åı£
    0.09
    åŁĥåıĬ
    0.09
    /ubuntu
    0.09
    Activations Density 0.372%

    No Known Activations