© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37536
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    holm
    -0.10
    æĬ½
    -0.10
    ingham
    -0.10
    okit
    -0.09
    è¿ĽåŁİ
    -0.09
    èĥ½èĢĹ
    -0.09
     mát
    -0.09
    _costs
    -0.09
    使æĪij
    -0.09
    Compat
    -0.08
    POSITIVE LOGITS
    менно
    0.10
    åĬłçĽŁ
    0.10
    edException
    0.10
    èĪ¹åıª
    0.09
    pole
    0.09
    åѤç«ĭ
    0.09
    åIJĮ缣
    0.09
    bic
    0.09
    伶
    0.09
    港åı£
    0.09
    Activations Density 0.117%

    No Known Activations