© 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. 20647
    Prev
    Next
    INDEX
    Explanations

    herbs and medicinal compounds

    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
    owell
    -0.10
    纵横
    -0.10
    èĶĹ
    -0.09
    èĢĹ
    -0.09
    Crystal
    -0.09
    ä¸Ģå¤ľ
    -0.09
    æĮij
    -0.08
     اÙĦإعÙĦاÙħ
    -0.08
    æŀª
    -0.08
    骡
    -0.08
    POSITIVE LOGITS
    精油
    0.13
    ä¸Ńèį¯
    0.10
    èį¯æĿIJ
    0.10
    èį¯åºĹ
    0.10
    äº§åľ°
    0.09
     herbs
    0.09
    ä¸Ńèį¯æĿIJ
    0.09
    æĮĩçĶ²
    0.09
    éĩĩæijĺ
    0.09
    èĴ´
    0.09
    Activations Density 0.108%

    No Known Activations