© 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. 39631
    Prev
    Next
    INDEX
    Explanations

    sanitary conditions and facilities

    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
    yte
    -0.09
    ç²²
    -0.09
    pler
    -0.09
    неÑĨ
    -0.08
     spoon
    -0.08
    æľį
    -0.08
    ç©Ĺ
    -0.08
    á»ĵ
    -0.08
    úc
    -0.08
    ળ
    -0.08
    POSITIVE LOGITS
    ings
    0.11
    模èĮĥ
    0.10
    ä¸ĸçķĮä¸ĬæľĢ
    0.09
    æĻ®æŁ¥
    0.09
    å±İ
    0.09
    åħĪéĶĭ
    0.09
    ServiceProvider
    0.09
    инг
    0.09
    /or
    0.08
    аÑĢам
    0.08
    Activations Density 0.003%

    No Known Activations