© 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. 27673
    Prev
    Next
    INDEX
    Explanations

    locations, provinces, or cities

    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
    efault
    -0.09
    å««
    -0.09
    fleet
    -0.09
    çŁ¿ä¸ļ
    -0.09
    è®°è½½
    -0.09
    飫
    -0.09
     Loch
    -0.08
    olk
    -0.08
     gou
    -0.08
    æݨ
    -0.08
    POSITIVE LOGITS
    åı£å²¸
    0.13
    è¾¹å¢ĥ
    0.13
     border
    0.11
     Border
    0.11
    (border
    0.10
    _border
    0.10
    Border
    0.09
    éĢļåħ³
    0.09
     cherry
    0.09
    apot
    0.09
    Activations Density 0.150%

    No Known Activations