© 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. 35565
    Prev
    Next
    INDEX
    Explanations

    and linking items

    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
    amas
    -0.09
    å¹¢
    -0.08
    ici
    -0.08
    åŀĤ缴
    -0.08
    STEM
    -0.08
    æ´¹
    -0.08
    ä¸įçŁ¥
    -0.08
     Arabs
    -0.08
     Asi
    -0.08
    管çIJĨ人åijĺ
    -0.07
    POSITIVE LOGITS
    æľºåŀĭ
    0.09
    åģĮ
    0.09
     kaps
    0.09
    çĭł
    0.08
    çļĦç¡®
    0.08
    åľ°çĤ¹
    0.08
    _gain
    0.08
    æĬij
    0.08
    èµ°ä¸Ĭ
    0.08
    @d
    0.08
    Activations Density 0.027%

    No Known Activations