© 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. 49666
    Prev
    Next
    INDEX
    Explanations

    library and management

    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
    éļħ
    -0.10
    ìĭĿ
    -0.09
    å··
    -0.09
    æ¡ħ
    -0.09
    yar
    -0.09
    å·¥åķĨå±Ģ
    -0.09
    çķĻè¨ĢæĿ¿
    -0.09
    wake
    -0.09
    inan
    -0.08
    _toolbar
    -0.08
    POSITIVE LOGITS
    åĽ¾ä¹¦é¦Ĩ
    0.12
     library
    0.09
    วà¸Ļ
    0.09
    library
    0.08
    èĹı
    0.08
     dime
    0.08
    pragma
    0.08
    .library
    0.08
    çķĮ
    0.08
    æĶ¶
    0.08
    Activations Density 0.061%

    No Known Activations