© 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. 50101
    Prev
    Next
    INDEX
    Explanations

    book of, sieve of

    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
    æķ´ä¸ªäºº
    -0.10
    ervo
    -0.09
    altar
    -0.09
    ç¥ŀæĥħ
    -0.09
    åģ¶
    -0.09
    羸
    -0.08
    EAR
    -0.08
    å½¢æĪIJ
    -0.08
    岫
    -0.08
    深深çļĦ
    -0.08
    POSITIVE LOGITS
    çĦī
    0.08
    ongan
    0.08
     Nobel
    0.08
    讲å¸Ī
    0.08
    omatic
    0.08
    nst
    0.08
    ä¼ļéķ¿
    0.08
    åĵij
    0.08
     RET
    0.07
    åѤçĭ¬
    0.07
    Activations Density 0.257%

    No Known Activations