© 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. 21415
    Prev
    Next
    INDEX
    Explanations

    acute medical conditions

    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
    osa
    -0.11
    é¦Ļæ°´
    -0.09
    noc
    -0.09
    oret
    -0.09
    顺åĬ¿
    -0.09
    ewise
    -0.08
    icator
    -0.08
    جÙĦ
    -0.08
    รม
    -0.08
    nts
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.13
    -ish
    0.11
    -minded
    0.10
    sville
    0.10
    vely
    0.10
    èĢĮè¨Ģ
    0.10
    idad
    0.10
    åĵĩ
    0.10
    ities
    0.09
    URAL
    0.09
    Activations Density 0.017%

    No Known Activations