© 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. 20830
    Prev
    Next
    INDEX
    Explanations

    Kentucky cities and counties

    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
    agnost
    -0.10
    æ³¾
    -0.10
    adium
    -0.09
     Rutgers
    -0.09
    ä¸įç¦ģ
    -0.09
    umber
    -0.09
     Detroit
    -0.09
     affairs
    -0.08
    èĿĩ
    -0.08
     Dutch
    -0.08
    POSITIVE LOGITS
     Kentucky
    0.13
    éĤĻ
    0.12
     Louisville
    0.11
    éĥľ
    0.11
    éĥijå·ŀ
    0.11
     Nashville
    0.10
    æ´Ľéĺ³
    0.10
    éĤķ
    0.10
    è°·
    0.10
    éĥijå·ŀå¸Ĥ
    0.10
    Activations Density 0.220%

    No Known Activations