© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52455
    Prev
    Next
    INDEX
    Explanations

    not responsible

    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
    稽
    -0.11
    æĮĩåIJij
    -0.09
    éĤ£ä¸Ģ
    -0.09
    ç®Ģ
    -0.09
    åij±
    -0.09
    PHY
    -0.08
    ä¸ī个æľĪ
    -0.08
    onth
    -0.08
    åĩĮ
    -0.08
    éĤ£ç§į
    -0.08
    POSITIVE LOGITS
    æī¿åıĹ
    0.12
    оÑĩно
    0.10
     Grain
    0.09
    ç«ĭå¿Ĺ
    0.09
     chá»ĭu
    0.09
    积æŀģåıĤä¸İ
    0.09
    æĭħè´Ł
    0.09
    æĽ¿
    0.08
    举éĥ¨
    0.08
    åıĹåĪ°å½±åĵį
    0.08
    Activations Density 0.012%

    No Known Activations