© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    endocarditis, viral, incidence, etiology

    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
    éľľ
    -0.09
    åİĨ
    -0.09
    bro
    -0.08
    1
    -0.08
    2
    -0.08
    8
    -0.08
    çĻĥ
    -0.08
    ona
    -0.08
    9
    -0.08
    mg
    -0.08
    POSITIVE LOGITS
    ç»ĨèıĮ
    0.11
    è·¨çķĮ
    0.11
    çķĮ第ä¸Ģ
    0.10
    èıĮ
    0.10
    导
    0.10
    ä¸īä½įä¸Ģä½ĵ
    0.10
    èij³
    0.10
    ynamo
    0.10
    çķĮ
    0.10
    æĦŁæŁĵ
    0.10
    Activations Density 0.345%

    No Known Activations