© 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. 35521
    Prev
    Next
    INDEX
    Explanations

    lymphocyte and lymphoma

    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
    otch
    -0.12
    çļ¿
    -0.11
    ably
    -0.10
    ëī´ìĬ¤
    -0.09
    wal
    -0.09
    ocities
    -0.09
    åĩ¡æľ¬ç½ij
    -0.09
    ajar
    -0.08
    ummy
    -0.08
    rors
    -0.08
    POSITIVE LOGITS
    atics
    0.13
    atic
    0.12
    ãģĹãģ¾ãģĨ
    0.09
    pheric
    0.08
    aceous
    0.08
    vision
    0.08
     embar
    0.08
    system
    0.08
    à¹ģà¸Ĺ
    0.08
    soever
    0.08
    Activations Density 0.049%

    No Known Activations