© 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. 49645
    Prev
    Next
    INDEX
    Explanations

    arguably

    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
    å®Ľ
    -0.11
    ahl
    -0.10
    æĪijçĽ¸ä¿¡
    -0.09
    深深
    -0.09
    _planes
    -0.09
    åĿĩ
    -0.08
    åĢ¡
    -0.08
    .Must
    -0.08
    оÑģÑĤ
    -0.08
    pei
    -0.08
    POSITIVE LOGITS
    æĽ´éĩįè¦ģçļĦ
    0.13
    æĽ´éĩįè¦ģ
    0.12
    æľĢéĩįè¦ģçļĦ
    0.11
    æĪIJè´¥
    0.11
    æĦıä¹īä¸ĬçļĦ
    0.11
    è¿ĺåĮħæĭ¬
    0.11
    è¿IJæ°Ķ
    0.10
    è¿ĩå¾Ĺ
    0.10
    uckle
    0.10
    åľ¨æķ´ä¸ª
    0.10
    Activations Density 0.007%

    No Known Activations