© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20759
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
    POP
    -0.09
     pocket
    -0.09
     Pocket
    -0.09
     POP
    -0.09
    å±Ĥåĩº
    -0.08
    çĸĻ
    -0.08
    bled
    -0.08
     convenience
    -0.08
    鸣类
    -0.08
    endra
    -0.08
    POSITIVE LOGITS
    èİ«æĸ¯
    0.10
    è°ª
    0.09
    oeff
    0.09
    APS
    0.08
    å¥ĩèij©
    0.08
     Rhodes
    0.08
    äºı
    0.08
    Impossible
    0.08
    Sizer
    0.08
    å²ĺ
    0.08
    Activations Density 0.026%

    No Known Activations