© 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. 2189
    Prev
    Next
    INDEX
    Explanations

    network interfaces

    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
    翳
    -0.09
    uida
    -0.09
    åī¡
    -0.09
    æĺĮ
    -0.08
     Brid
    -0.08
    ayas
    -0.08
    croft
    -0.08
     ØŃر
    -0.08
     Muj
    -0.08
     Pres
    -0.08
    POSITIVE LOGITS
    ä¸Ĭè°ĥ
    0.10
    ä¸įä¸Ĭ
    0.09
    æĥ«
    0.09
     ìŀIJ기
    0.09
    éĢģåĩº
    0.09
    izzo
    0.09
    _AUTO
    0.08
    ä¸Ĭåı¸
    0.08
    PACE
    0.08
    ibu
    0.08
    Activations Density 0.155%

    No Known Activations