© 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. 11266
    Prev
    Next
    INDEX
    Explanations

    whole or entire thing

    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
    ä¸Ģ次次
    -0.09
    éĤ£å°±æĺ¯
    -0.09
     dif
    -0.08
    ãģĦãģ£ãģŁ
    -0.08
    å°¤
    -0.08
    涣
    -0.08
    apon
    -0.08
    dif
    -0.08
    -sidebar
    -0.08
    çī§
    -0.08
    POSITIVE LOGITS
    èĮĥåĽ´åĨħ
    0.12
    åĽ´çĿĢ
    0.12
    oire
    0.11
    çݯç»ķ
    0.09
    é»ĺå¥ij
    0.09
    rys
    0.09
     вокÑĢÑĥг
    0.09
    ä¸įåħĭ
    0.09
    awah
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    Activations Density 0.024%

    No Known Activations