© 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. 21748
    Prev
    Next
    INDEX
    Explanations

    come back to inquire

    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
    isl
    -0.09
    èĩªçĦ¶èĢĮ
    -0.09
    æį
    -0.09
    ä¸ĵå±ŀ
    -0.09
    holm
    -0.08
    ÑĢенд
    -0.08
    åIJĪä¸Ģ
    -0.08
    engl
    -0.08
    Ĥ¤
    -0.08
    读书
    -0.08
    POSITIVE LOGITS
    çľĭå¾ħ
    0.11
    çī§
    0.10
    对å¾ħ
    0.10
    æľīéĹľ
    0.10
    æľīåħ³
    0.09
    ä¸ĢæŃ¥æŃ¥
    0.09
    пи
    0.09
    itzer
    0.08
    ç½Ķ
    0.08
     sausage
    0.08
    Activations Density 0.258%

    No Known Activations