© 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. 61643
    Prev
    Next
    INDEX
    Explanations

    place name endings

    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
    .serialize
    -0.09
    acen
    -0.09
    Å¡ÃŃ
    -0.08
    ières
    -0.08
    ocking
    -0.08
    еп
    -0.08
    _checkout
    -0.08
    usters
    -0.08
    linger
    -0.08
    elsea
    -0.08
    POSITIVE LOGITS
    rant
    0.10
    è¿ŀå¤ľ
    0.10
    ä¸įä¸ĭ
    0.09
    ç²±
    0.09
    æ¦Ĥ念èĤ¡
    0.09
    å°ıå§ijå¨ĺ
    0.09
    æĤ£
    0.09
     Bend
    0.08
    å¿Ĵ
    0.08
    кÑĢаÑĤ
    0.08
    Activations Density 0.044%

    No Known Activations