© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35535
    Prev
    Next
    INDEX
    Explanations

    city 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
    zos
    -0.09
    ness
    -0.09
    ted
    -0.09
    èĥ
    -0.09
    ìĤ¬íķŃ
    -0.09
    gable
    -0.09
    åŃ³
    -0.09
    าว
    -0.09
    绳
    -0.08
    ÙĬدÙĬ
    -0.08
    POSITIVE LOGITS
    MENT
    0.11
    antly
    0.10
    åĬ¨éĿĻ
    0.10
    ments
    0.09
    oretical
    0.09
    REA
    0.08
    alez
    0.08
    æ¯ĭ
    0.08
     County
    0.08
    æĥľ
    0.08
    Activations Density 0.012%

    No Known Activations