© 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. 18991
    Prev
    Next
    INDEX
    Explanations

    transportation corridors and transit stations

    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
    opies
    -0.11
    轶
    -0.10
    ;br
    -0.09
    moon
    -0.09
    ä¸ĩåĪĨ
    -0.09
    èĩªåĪ¶
    -0.09
    .AUTO
    -0.09
    ç¡Ĵ
    -0.09
     COPYING
    -0.08
    åĮ¿åIJį
    -0.08
    POSITIVE LOGITS
    çķħ
    0.09
    ç¬ĭ
    0.09
     LATIN
    0.09
     Reeves
    0.09
    åĢĻ
    0.09
    çħ§æł·
    0.08
    åĨµ
    0.08
     priority
    0.08
    ä¸įéĶĻ
    0.08
     lanes
    0.08
    Activations Density 0.068%

    No Known Activations