© 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. 48625
    Prev
    Next
    INDEX
    Explanations

    html and web code

    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
    OMP
    -0.10
    å¯ĵ
    -0.10
    erten
    -0.09
    éħįå¥Ĺ
    -0.09
     dilig
    -0.09
    éħįæĸ¹
    -0.09
    /ros
    -0.09
    éĹº
    -0.09
     caucus
    -0.09
    kas
    -0.09
    POSITIVE LOGITS
    HTML
    0.12
     HTML
    0.12
     XHTML
    0.11
     html
    0.11
    åIJĪ
    0.11
    html
    0.10
    _HTML
    0.09
    /html
    0.09
    (html
    0.09
    -html
    0.09
    Activations Density 0.334%

    No Known Activations