© 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. 28025
    Prev
    Next
    INDEX
    Explanations

    android development

    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
    _WINDOWS
    -0.10
     Tender
    -0.10
    cede
    -0.09
    äºĴèģĶ
    -0.09
    /apple
    -0.09
    .MouseDown
    -0.09
    .pad
    -0.09
     ipad
    -0.09
    WND
    -0.09
    æİ©çĽĸ
    -0.09
    POSITIVE LOGITS
     android
    0.09
     Android
    0.09
    SharedPreferences
    0.09
    (android
    0.09
     CharSequence
    0.09
    ä¼ı
    0.09
    roid
    0.09
    ç¬ķ
    0.09
    ViewPager
    0.09
     androidx
    0.09
    Activations Density 0.926%

    No Known Activations