© 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. 55292
    Prev
    Next
    INDEX
    Explanations

    Broadway musicals

    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
    ä½ĵåĨħ
    -0.09
    egal
    -0.08
    å¼Ĥåľ°
    -0.08
    zej
    -0.08
    éĺħ
    -0.08
    пÑĥÑģ
    -0.08
     coder
    -0.08
    ho
    -0.08
    æĭ¨æīĵ
    -0.08
    æĹłè®ºå¦Ĥä½ķ
    -0.08
    POSITIVE LOGITS
    .Sdk
    0.10
    åIJį为
    0.10
    ä½³
    0.10
    æĥ¬
    0.10
    iddy
    0.10
    æľĢä½³
    0.09
    èĪŀåı°ä¸Ĭ
    0.09
    æĶ¶åī²
    0.09
    çķĮçļĦ
    0.09
    verse
    0.09
    Activations Density 0.007%

    No Known Activations