© 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. 27743
    Prev
    Next
    INDEX
    Explanations

    on the part 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
    æİīäºĨ
    -0.10
    ãģĦãģ£ãģŁ
    -0.10
    ä¸Ńæľī
    -0.10
    ä¸Ńå°ıåŀĭ
    -0.09
    èĩªæľī
    -0.09
     пÑĢакÑĤиÑĩеÑģ
    -0.09
     Rou
    -0.09
    -ser
    -0.09
    æĢ»è£ģ
    -0.09
    æĪĸèĢħ说
    -0.08
    POSITIVE LOGITS
    侦
    0.08
    eland
    0.08
    çĮ¿
    0.08
    cid
    0.08
    æľĿ
    0.08
    åħ»
    0.08
    /on
    0.08
    _OW
    0.08
    ENA
    0.08
    emas
    0.08
    Activations Density 0.003%

    No Known Activations