© 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. 55485
    Prev
    Next
    INDEX
    Explanations

    green tea harvesting and steeping

    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
    PMC
    -0.10
    饰
    -0.09
    _CLI
    -0.09
     lean
    -0.09
    æľįåĬ¡èĥ½åĬĽ
    -0.09
    æ²³
    -0.09
     наÑĢ
    -0.08
    esp
    -0.08
    éľ°
    -0.08
    lean
    -0.08
    POSITIVE LOGITS
    èĮ¶åı¶
    0.09
     tea
    0.09
    å¸ĪåĤħ
    0.09
    ownt
    0.09
    é¼ĵ
    0.09
    lander
    0.08
    .BL
    0.08
    ç¿¥
    0.08
    书åĨĻ
    0.08
    çļĵ
    0.08
    Activations Density 0.038%

    No Known Activations