© 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. 61754
    Prev
    Next
    INDEX
    Explanations

    features

    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
    注æĺİæĿ¥æºIJ
    -0.09
    ä¸Ńæĸ¹
    -0.09
    ä¸Ģå¼ł
    -0.09
    åĩłå®¶
    -0.09
    çĿĢä»ĸ
    -0.09
    สวย
    -0.09
    åĬŁå¤«
    -0.09
    åĽŀäºĭ
    -0.08
     знаÑĩ
    -0.08
    æķ´æ´ģ
    -0.08
    POSITIVE LOGITS
    atical
    0.09
    athers
    0.09
     ench
    0.08
    oriented
    0.08
    ermann
    0.08
    ucht
    0.08
    çķľ
    0.08
    åĴĮåıijå±ķ
    0.08
    etus
    0.08
    initely
    0.08
    Activations Density 0.044%

    No Known Activations