© 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. 19099
    Prev
    Next
    INDEX
    Explanations

    House, Consortium, Fred

    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
     autopsy
    -0.09
    å¾ģéĽĨ
    -0.09
    cob
    -0.08
    gem
    -0.08
    igi
    -0.08
    plr
    -0.08
    eat
    -0.08
    elry
    -0.08
    isser
    -0.08
    ahn
    -0.08
    POSITIVE LOGITS
    墩
    0.10
    æķij人
    0.10
    åŃĶéĽĢ
    0.10
    åijĺ
    0.10
    èµ·æĿ¥äºĨ
    0.09
    кол
    0.09
    å·´æĭī
    0.09
    æĬ¤
    0.09
    .wrap
    0.09
    umar
    0.09
    Activations Density 0.018%

    No Known Activations