© 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. 18376
    Prev
    Next
    INDEX
    Explanations

    vacation or holidays

    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
    èĩ´åij½
    -0.09
    èµ·åºĬ
    -0.09
    å¸ĮæľĽèĥ½å¤Ł
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    åĽ½ç±į
    -0.08
    ÉĽ
    -0.08
    æĮ½
    -0.08
    ateral
    -0.08
     пÑĢоб
    -0.08
    uet
    -0.08
    POSITIVE LOGITS
    -addons
    0.10
    èĴ¸
    0.09
    .contentSize
    0.08
    osit
    0.08
    åIJĮè¡Į
    0.08
    toMatchSnapshot
    0.08
    à¸Ŀาà¸ģ
    0.08
    缮çļĦåľ°
    0.08
    ä¸į失
    0.08
    çĶ¬
    0.08
    Activations Density 0.014%

    No Known Activations