© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19693
    Prev
    Next
    INDEX
    Explanations

    movies and fiction

    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
    涸
    -0.10
    Aw
    -0.10
    è·Łä»ĸ
    -0.09
     Aberdeen
    -0.09
    ESIS
    -0.09
    æIJŃ
    -0.09
    iless
    -0.08
    è·Łå¥¹
    -0.08
    aleigh
    -0.08
    Classic
    -0.08
    POSITIVE LOGITS
    åī§ä¸Ń
    0.12
    å°ı说
    0.11
    èĻļæŀĦ
    0.10
    å°ģ
    0.10
    å¦ĤæĦı
    0.09
     Hell
    0.09
    æīĢæľīæĥħèĬĤ
    0.09
    uned
    0.09
    åı©
    0.08
    æĥħèĬĤ
    0.08
    Activations Density 0.105%

    No Known Activations