© 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. 56497
    Prev
    Next
    INDEX
    Explanations

    Scorsese film parts

    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
    æ¼ł
    -0.11
    çıĢ
    -0.09
    estone
    -0.09
    åīį身
    -0.09
    illa
    -0.08
    æĺ¥å¤©
    -0.08
    æijĦ
    -0.08
    åłĨæĶ¾
    -0.08
    è¡Įäºĭ
    -0.08
    itus
    -0.08
    POSITIVE LOGITS
    缨
    0.09
    夷
    0.08
     Wol
    0.08
    èĪĨ
    0.08
    .apple
    0.08
    åĨĹ
    0.08
    irm
    0.08
     still
    0.08
    pecies
    0.08
    /xml
    0.08
    Activations Density 0.002%

    No Known Activations