© 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. 48521
    Prev
    Next
    INDEX
    Explanations

    court hearing postponed

    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
    åħīèį£
    -0.09
    çºłéĶĻ
    -0.09
    è·³è·ĥ
    -0.09
    .DEBUG
    -0.09
    æĤ£ä¸Ĭ
    -0.08
    éĢĢ
    -0.08
    æį¢æĿ¥
    -0.08
    欧
    -0.08
    .fade
    -0.08
    æ£Ģä¿®
    -0.08
    POSITIVE LOGITS
    è£ģ
    0.10
    -ng
    0.09
    ç¥Ī
    0.09
     Fly
    0.09
    æĿµ
    0.09
    åĸ»
    0.09
    é£ŀ
    0.08
    .motion
    0.08
    ern
    0.08
     Peek
    0.08
    Activations Density 0.695%

    No Known Activations