© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37644
    Prev
    Next
    INDEX
    Explanations

    questioning or wanting to know

    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
    unken
    -0.10
    æĪª
    -0.09
    家åĸ»æĪ·æĻĵ
    -0.09
    åı¤åħ¸
    -0.09
    hek
    -0.09
    æĭ¿æĿ¥
    -0.09
    uggy
    -0.09
    åģľçīĮ
    -0.08
    empo
    -0.08
    ä¸ĢæŦ
    -0.08
    POSITIVE LOGITS
    é»ĺé»ĺ
    0.09
    éĤ£åıª
    0.09
     Verm
    0.08
    é¡·
    0.08
    ione
    0.08
    æĪĸæĺ¯
    0.08
    ä¸įåŃĺåľ¨
    0.08
    é»ĺé»ĺåľ°
    0.08
    ARIO
    0.08
    å®ĹæŨ
    0.08
    Activations Density 0.032%

    No Known Activations