© 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. 19091
    Prev
    Next
    INDEX
    Explanations

    Ontario location 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
    istr
    -0.12
    lington
    -0.10
    ç¥ĸåĽ½
    -0.09
    å¯ĮåĬĽ
    -0.09
    istro
    -0.09
    pace
    -0.09
    ä½ķåĨµ
    -0.09
    -lined
    -0.08
    ç»ıå¼Ģ
    -0.08
    irs
    -0.08
    POSITIVE LOGITS
    mega
    0.10
    ayo
    0.09
    ç¬ijç¬ij
    0.09
    åIJĦåĮº
    0.09
    çĶµå·¥
    0.09
    anness
    0.09
    Ñģкие
    0.09
    perator
    0.08
    exus
    0.08
    lace
    0.08
    Activations Density 0.012%

    No Known Activations