© 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. 30448
    Prev
    Next
    INDEX
    Explanations

    most [adjective/superlative]

    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
    ä¸įåIJĮäºİ
    -0.09
    plays
    -0.08
    èĭ¥å¹²
    -0.08
     Arte
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
    erra
    -0.07
    å°¤
    -0.07
    egg
    -0.07
    æĽ´å¥½
    -0.07
    ç¯ģ
    -0.07
    POSITIVE LOGITS
     ÑģамÑĭм
    0.10
    æľĢåħĪè¿ĽçļĦ
    0.09
     ÑģамÑĭе
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    aus
    0.09
    åĩ¹
    0.09
    æľµ
    0.09
    åį³ä¾¿æĺ¯
    0.09
    ä¸Ģè¶Ł
    0.09
    é²ģ
    0.08
    Activations Density 0.175%

    No Known Activations