© 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. 35038
    Prev
    Next
    INDEX
    Explanations

    distribute, sell, license, display

    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
    Äįe
    -0.10
    å¿ħä¸įåı¯
    -0.09
    éļľ
    -0.09
    errmsg
    -0.09
    itunes
    -0.08
    侮辱
    -0.08
    é¦ĸ家
    -0.08
    âĶĦ
    -0.08
    éĽĮ
    -0.08
    isted
    -0.08
    POSITIVE LOGITS
    arat
    0.09
    URT
    0.09
    禧
    0.09
    umen
    0.08
    åıªä¼ļ
    0.08
    -animate
    0.08
    è·Łä¸įä¸Ĭ
    0.08
    los
    0.08
    ouro
    0.08
    зам
    0.08
    Activations Density 0.063%

    No Known Activations