© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7783
    Prev
    Next
    INDEX
    Explanations

    first and last names

    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
    åIJ¸çº³
    -0.09
    _rest
    -0.09
    çĸ«
    -0.09
    èĢģ人家
    -0.09
    好äºĭ
    -0.09
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.09
     Scratch
    -0.08
    èµŀç¾İ
    -0.08
    åįĩèµ·
    -0.08
    åĨįéĢł
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸ĢåIJį
    0.12
    ä¸ĢåIJį
    0.11
    è¿ĻåIJį
    0.09
    被åĪ¤
    0.09
    .shtml
    0.09
    éĦ°
    0.09
    鹤
    0.09
    arius
    0.08
    该æ¡Ī
    0.08
    æĪĸå°Ĩ
    0.08
    Activations Density 0.205%

    No Known Activations