© 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. 17217
    Prev
    Next
    INDEX
    Explanations

    street intersections and addresses

    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
    æľįåĬ¡åĮº
    -0.09
    strom
    -0.09
    orde
    -0.09
    à¸Ńà¸Ńà¸ģ
    -0.09
    .Init
    -0.09
    æµĻæ±Łå¤§åѦ
    -0.09
    ä¸įåİ»
    -0.08
    à¸ķำ
    -0.08
    бÑĢа
    -0.08
    åĩĨåħ¥
    -0.08
    POSITIVE LOGITS
     silver
    0.08
     Weber
    0.08
    æħij
    0.08
    ãģĹãģı
    0.08
    æķ£å¸ĥ
    0.08
    èIJģ
    0.08
    éĩįå·¥
    0.08
    leitung
    0.08
    .lat
    0.08
    uming
    0.08
    Activations Density 0.082%

    No Known Activations