© 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. 61944
    Prev
    Next
    INDEX
    Explanations

    praise of Israel

    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
    æĬ½æŁ¥
    -0.09
     vending
    -0.09
    packed
    -0.09
    eldon
    -0.09
    ä¹Łæľīå¾Īå¤ļ
    -0.08
     бон
    -0.08
    èķĥ
    -0.08
    è¾ĥéķ¿
    -0.08
    -packed
    -0.08
    ä¼IJ
    -0.08
    POSITIVE LOGITS
    èµ·åºĬ
    0.10
    è¶ĭ
    0.09
    loth
    0.09
    åŃIJåŃĻ
    0.09
     crown
    0.09
     lazy
    0.09
    Lazy
    0.08
    lazy
    0.08
    éªĦåĤ²
    0.08
    ils
    0.08
    Activations Density 0.047%

    No Known Activations