© 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. 8488
    Prev
    Next
    INDEX
    Explanations

    photosynthesis and light conversion

    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
    åĽ´çĿĢ
    -0.10
    è§ģè¯ģ
    -0.09
     hawk
    -0.09
    æŀ¢
    -0.09
    igon
    -0.09
    _EMIT
    -0.09
    æĬĺ
    -0.09
     BIN
    -0.09
    UMENT
    -0.08
    _emit
    -0.08
    POSITIVE LOGITS
    åħ¨è¿ĩç¨ĭ
    0.10
    thr
    0.09
     Bray
    0.09
    æĦį
    0.09
    åĽŃåĮº
    0.09
    åı¶åŃIJ
    0.09
    åĴĢ
    0.08
    arde
    0.08
    æľ¬ç½ijç«Ļ
    0.08
    åIJ¸æĶ¶
    0.08
    Activations Density 0.055%

    No Known Activations