© 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. 26534
    Prev
    Next
    INDEX
    Explanations

    tertiary hospital

    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
    ensch
    -0.10
     ÑģеÑĢии
    -0.10
     кваÑĢ
    -0.09
    annes
    -0.09
    产éĶĢ
    -0.08
    æµĭç»ĺ
    -0.08
    鼷
    -0.08
    èĦĨå¼±
    -0.08
     игÑĢÑĭ
    -0.08
    åĬĽ
    -0.08
    POSITIVE LOGITS
    åĮ»éĻ¢
    0.15
     hospital
    0.12
    éĨ«éĻ¢
    0.12
     Hospital
    0.11
     hospitals
    0.10
    æķijæ²»
    0.10
    ç´¯
    0.09
    çĸijéļ¾
    0.09
     Pitch
    0.09
    缺åı£
    0.09
    Activations Density 0.381%

    No Known Activations