© 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. 61671
    Prev
    Next
    INDEX
    Explanations

    my/your/our + noun

    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
    èĤ²åĦ¿
    -0.09
    è³½
    -0.09
    èµĽ
    -0.09
    -minus
    -0.08
     пÑĢек
    -0.08
    è¿ĺæľīä¸ĢäºĽ
    -0.08
    ä½Ĩä»ĸ们
    -0.08
    éķĩåħļå§Ķ
    -0.08
    èµĽåIJİ
    -0.08
    uck
    -0.08
    POSITIVE LOGITS
    çī©ä»·
    0.09
    elin
    0.09
    ters
    0.09
    izr
    0.09
    è§Ĩ线
    0.09
    éĢģæĿ¥
    0.09
     sı
    0.09
    表éĿ¢ä¸Ĭ
    0.09
    社ä¼ļ稳å®ļ
    0.09
    pty
    0.09
    Activations Density 0.019%

    No Known Activations