© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53221
    Prev
    Next
    INDEX
    Explanations

    one-piece outfit

    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
    人工
    -0.09
    abi
    -0.09
    çµĤãĤıãģ£ãģŁ
    -0.09
    é¾Ľ
    -0.09
    éĶħ
    -0.09
    ç«ĭ马
    -0.09
    iele
    -0.08
    åĬ£åĬ¿
    -0.08
    .repeat
    -0.08
    _BIND
    -0.08
    POSITIVE LOGITS
    éļĨ
    0.09
    aries
    0.09
    é¼ĵ
    0.08
    erness
    0.08
    erton
    0.08
    ers
    0.08
    azzo
    0.08
    ocol
    0.08
    ç¿»
    0.08
    ä¹Łè¢«
    0.08
    Activations Density 0.001%

    No Known Activations