© 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. 26419
    Prev
    Next
    INDEX
    Explanations

    got me beat

    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
    æķ£
    -0.10
    å¾Ĺ以
    -0.09
    ç«Łæĺ¯
    -0.09
     Lam
    -0.09
    pra
    -0.08
    æĬĵ好
    -0.08
    abama
    -0.08
    ober
    -0.08
    _Run
    -0.08
    _unused
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.10
    建çŃijæĿIJæĸĻ
    0.09
    ">ÃĹ</
    0.09
    åĮĸåѦåĵģ
    0.08
    åĪĿæŃ¥
    0.08
    åºĻ
    0.08
    è¤Ĭ
    0.08
    éĢıè§Ĩ
    0.08
    à¸Ľà¸£à¸°à¸ª
    0.08
     reins
    0.08
    Activations Density 0.194%

    No Known Activations