© 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. 31595
    Prev
    Next
    INDEX
    Explanations

    Milwaukee (city, county, transport, police, Bucks)

    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
    iali
    -0.09
    rophe
    -0.08
    çĩ§
    -0.08
    ulin
    -0.08
    оÐ
    -0.08
    cole
    -0.08
    åįģä¸ĩ
    -0.08
    ives
    -0.08
    çķ¹
    -0.08
    æ¯Ķäºļ
    -0.08
    POSITIVE LOGITS
    ishly
    0.11
    isher
    0.10
    0.09
    éªĭ
    0.09
    ÙħÙĨ
    0.09
    keit
    0.09
     Tiên
    0.09
     Kent
    0.09
    ently
    0.09
    ALK
    0.09
    Activations Density 0.003%

    No Known Activations