© 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. 26522
    Prev
    Next
    INDEX
    Explanations

    software and tools

    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
    ä¸įåŃĺåľ¨
    -0.11
    ä¼Ĭæĭī
    -0.10
    庶
    -0.10
    din
    -0.09
    å°ijè§ģ
    -0.09
    ä¸įåİ»
    -0.09
    ç¨Ģ
    -0.09
    gro
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.08
    arge
    -0.08
    POSITIVE LOGITS
     Rudd
    0.09
    çºł
    0.09
    åŁŃ
    0.09
    ÙħاÙĨ
    0.09
    rong
    0.08
    .userAgent
    0.08
    强æľīåĬĽ
    0.08
    ç¥ŀä»Ļ
    0.08
    èªĵ
    0.08
    _ef
    0.08
    Activations Density 0.039%

    No Known Activations