© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    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
    æĮĩåIJij
    -0.09
    коÑģ
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
     Lem
    -0.08
    reich
    -0.08
    æĻ¨æĬ¥
    -0.08
    åħĭæľį
    -0.08
    èģĶæĥ³
    -0.08
    ondo
    -0.08
    ä¸įåıĹ
    -0.08
    POSITIVE LOGITS
    å¼Ħ
    0.08
    èĨĤ
    0.08
    寸
    0.08
    æĸĹ
    0.08
    讶
    0.08
    åľ¨åŃ¦æł¡
    0.08
    ãģĦãģ¾ãģĹãģŁ
    0.08
    åı³æīĭ
    0.08
    è²Ĥ
    0.07
    (using
    0.07
    Activations Density 0.252%

    No Known Activations