© 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. 38206
    Prev
    Next
    INDEX
    Explanations

    hospital-related contexts

    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
    -0.12
    çļij
    -0.10
    å¸Ĥä¸Ńå¿ĥ
    -0.10
    å²ĺ
    -0.09
    lep
    -0.09
    æİ¢æµĭ
    -0.09
     Coff
    -0.09
    ixer
    -0.09
    ->__
    -0.09
    -legged
    -0.09
    POSITIVE LOGITS
    ization
    0.10
    ity
    0.10
    mates
    0.10
    PING
    0.10
    wide
    0.09
    æ³ķ人
    0.09
    aned
    0.09
    个åĪ«
    0.09
    ING
    0.09
     desi
    0.09
    Activations Density 0.032%

    No Known Activations