© 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. 50177
    Prev
    Next
    INDEX
    Explanations

    vegetables and crops

    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¥Ķè·ij
    -0.11
    娣
    -0.10
     Woodward
    -0.10
    å·¥ç¨ĭè´¨éĩı
    -0.09
    iland
    -0.09
    çĴľ
    -0.09
    utan
    -0.09
    inations
    -0.09
    è´ª
    -0.09
    追赶
    -0.08
    POSITIVE LOGITS
     Superior
    0.10
    ANDLE
    0.09
    клад
    0.09
    -Jan
    0.09
    ä¼Łå¤§çļĦ
    0.09
    .removeChild
    0.09
    æ¢Ĩ
    0.09
    çŃ¾çº¦
    0.09
    ctest
    0.08
     McKenzie
    0.08
    Activations Density 0.046%

    No Known Activations