© 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. 62777
    Prev
    Next
    INDEX
    Explanations

    suburban and coastal locations

    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
    褶
    -0.10
    æŶ任
    -0.09
    /Math
    -0.09
    -know
    -0.08
    ä¸ĸä¸Ĭ
    -0.08
    è®®æ¡Ī
    -0.08
    аÑĤелÑĮ
    -0.08
    ãģŁãģı
    -0.08
    yan
    -0.08
     ÑĦл
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»ä¸Ń
    0.11
    IZER
    0.11
    ization
    0.11
    ização
    0.11
    æ¢ĵ
    0.10
    izedName
    0.10
    eur
    0.10
    åįİ缼
    0.10
    iser
    0.10
    ización
    0.10
    Activations Density 0.091%

    No Known Activations