© 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. 48169
    Prev
    Next
    INDEX
    Explanations

    Software Foundation License

    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¸Ńåħ³æĿij
    -0.10
    èĦ¯
    -0.09
    infeld
    -0.08
     intelig
    -0.08
    åıįèħIJ
    -0.08
    ÑĢоÑģ
    -0.08
    æīĢè°ĵ
    -0.08
    åĮ¡
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
    رÙĪس
    -0.08
    POSITIVE LOGITS
    chal
    0.09
    æ°
    0.09
    åħ¬å®īå±Ģ
    0.08
    alt
    0.08
    é«ĺåİĭ
    0.08
    thon
    0.08
    ä¸Ĭä¸ĭ游
    0.08
    atom
    0.08
    itto
    0.08
    éĶħçĤī
    0.08
    Activations Density 0.104%

    No Known Activations