© 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. 29989
    Prev
    Next
    INDEX
    Explanations

    years followed by quantifying words

    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
    è¿ŀå¤ľ
    -0.13
    åłŀ
    -0.11
    rys
    -0.11
    éķ¿æľŁä»¥æĿ¥
    -0.10
    ãģĹãģ°ãĤīãģı
    -0.10
    å½ĵæĻļ
    -0.10
     ÑĩÑĥвÑģÑĤво
    -0.10
    å½ĵæĹ¥
    -0.09
    æ·±å¤ľ
    -0.09
    çļĦç«ŀäºī
    -0.09
    POSITIVE LOGITS
    /month
    0.11
     ago
    0.11
    å°»
    0.09
     ká»ĥ
    0.09
    oll
    0.09
    ago
    0.09
    ä¸ĭæĿ¥
    0.08
    ãģ¶ãĤĬ
    0.08
    ÑĢÑıд
    0.08
    aign
    0.08
    Activations Density 0.198%

    No Known Activations