© 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. 36394
    Prev
    Next
    INDEX
    Explanations

    Teresa and Theresa names

    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
    ì²ĺ
    -0.09
    èĸ®
    -0.09
    rite
    -0.09
    endra
    -0.09
    rove
    -0.09
    raz
    -0.09
    ioc
    -0.09
    秫
    -0.08
    请æĤ¨
    -0.08
    urious
    -0.08
    POSITIVE LOGITS
    è¦ģåĬłå¼º
    0.11
    inals
    0.10
    åģļ强
    0.10
    大å±Ģ
    0.09
    моÑĤ
    0.09
    soever
    0.08
    ŀ
    0.08
    幺
    0.08
    umo
    0.08
     bloody
    0.08
    Activations Density 0.003%

    No Known Activations