© 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. 19825
    Prev
    Next
    INDEX
    Explanations

    reclined or reclining

    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
    spots
    -0.10
    éĹ´éļĻ
    -0.09
    çŁ
    -0.09
    roe
    -0.09
    indr
    -0.09
    æĿ¡è¯Ħ论
    -0.08
    åĮ¹éħį
    -0.08
    åѤåįķ
    -0.08
    ä¸Ģçľ¼
    -0.08
    èķ¨
    -0.08
    POSITIVE LOGITS
    躺
    0.13
    é¢ł
    0.12
    èººåľ¨
    0.11
    躺çĿĢ
    0.11
    åĢĴåľ¨åľ°
    0.10
    åĢĴåľ¨
    0.09
     upside
    0.09
    ä»°
    0.09
    çļĦ姿æĢģ
    0.09
    离å¼Ģ
    0.09
    Activations Density 0.075%

    No Known Activations