© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21250
    Prev
    Next
    INDEX
    Explanations

    township names and locations

    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
    ificates
    -0.10
    paces
    -0.10
    åIJĪãĤıãģĽ
    -0.09
    OST
    -0.09
    çİĭåĽ½
    -0.09
    ä¸ĵåįĸ
    -0.09
    point
    -0.09
    pace
    -0.09
    çİĭæľĿ
    -0.09
     Quart
    -0.09
    POSITIVE LOGITS
    elijke
    0.11
    mates
    0.11
    aze
    0.09
    kah
    0.09
    arent
    0.09
    룰
    0.09
    åİŁæĿ¥çļĦ
    0.08
    atten
    0.08
    ester
    0.08
    åİŁä¾Ĩ
    0.08
    Activations Density 0.009%

    No Known Activations