© 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. 10634
    Prev
    Next
    INDEX
    Explanations

    attesting to principles

    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
    ersh
    -0.09
    åģķ
    -0.08
    ç¢į
    -0.08
     Boiler
    -0.08
    ä¸ĭåİ»
    -0.08
    åģ¶
    -0.08
    ç¾İçļĦ
    -0.08
    èĭ¥æĤ¨
    -0.08
    æĪĺçķ¥æĢ§
    -0.08
    alion
    -0.08
    POSITIVE LOGITS
    emies
    0.10
    ä¸įçŁ¥ä¸įè§ī
    0.09
    atz
    0.09
    .Float
    0.09
    мел
    0.08
     hur
    0.08
    ä¸įä½Ĩ
    0.08
    ä¸į说
    0.08
    æĹ¥å¤ľ
    0.08
    itic
    0.07
    Activations Density 0.152%

    No Known Activations