© 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. 34332
    Prev
    Next
    INDEX
    Explanations

    purpose and function

    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
    æľīäºĨ
    -0.10
    æħİ
    -0.10
    ä¸įçķĻ
    -0.09
    磾
    -0.09
    çªĴæģ¯
    -0.09
    åĩºåĩ»
    -0.09
    è¡ħ
    -0.08
    ç¦ģå¿Į
    -0.08
    å¼ŁåħĦ
    -0.08
    iets
    -0.08
    POSITIVE LOGITS
    -minded
    0.10
    åħ°
    0.10
    çIJĨæĢ§
    0.10
     Medi
    0.10
    pad
    0.09
    ommen
    0.09
    /utility
    0.09
    utility
    0.09
    antry
    0.08
    æĭľ
    0.08
    Activations Density 0.052%

    No Known Activations