© 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. 53927
    Prev
    Next
    INDEX
    Explanations

    framework

    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
    inations
    -0.10
    æ¾İæ¹ĥ
    -0.09
    èĪIJ
    -0.09
    ----------------------------------------------------------------
    -0.09
    à¹Ģà¸Ńà¸ģ
    -0.09
    yna
    -0.09
    迹
    -0.08
    稳
    -0.08
    æł·çļĦ
    -0.08
    çľī
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    æ¡Ĩæŀ¶
    0.11
    å¿įåıĹ
    0.10
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    0.10
    èĢĮåĩº
    0.10
     frameworks
    0.10
    amp
    0.10
    edy
    0.09
    ills
    0.09
    -framework
    0.09
    Activations Density 0.028%

    No Known Activations