© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    job openings and descriptions

    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
    丰满
    -0.09
    полн
    -0.09
    çļĦéĤ£ç§į
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    erce
    -0.09
    èħŃ
    -0.09
    éĢģç»Ļ
    -0.08
     اÙĦØ·
    -0.08
    纵深
    -0.08
    宫
    -0.08
    POSITIVE LOGITS
    çļĦçĶŁæ´»
    0.09
    èĭ¥æľī
    0.09
    èIJ½
    0.09
    .publish
    0.09
    sdk
    0.08
    enci
    0.08
     Posting
    0.08
    èĸªéħ¬
    0.08
    çĤĻ
    0.08
    ocha
    0.08
    Activations Density 0.037%

    No Known Activations