© 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. 56193
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    æ¼¾
    -0.09
    getAs
    -0.09
    ç«ĭãģ¦
    -0.09
    anken
    -0.08
    æĬĺ
    -0.08
    ç«ĭæ¡Ī
    -0.08
    æĸ°çļĦ
    -0.08
    æĢ»çļĦ
    -0.08
    ios
    -0.08
    OOM
    -0.08
    POSITIVE LOGITS
    çģ¼
    0.10
    滨海
    0.09
     Roch
    0.08
    çĮ¾
    0.08
    _boxes
    0.08
    ä¸įåİ»
    0.08
    _wire
    0.08
    åģ¾
    0.08
     Bradley
    0.08
     Tune
    0.08
    Activations Density 0.007%

    No Known Activations