© 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. 31448
    Prev
    Next
    INDEX
    Explanations

    critical care unit and treatment

    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
    çĹ£
    -0.11
    æĪIJçĨŁ
    -0.09
    åĩ»
    -0.09
    plib
    -0.09
     insured
    -0.09
     seam
    -0.09
    stride
    -0.09
    èĩªåįij
    -0.09
    身ä½ĵåģ¥åº·
    -0.09
    è¿ijè§Ĩ
    -0.08
    POSITIVE LOGITS
     Karn
    0.10
    è°µ
    0.09
    hoff
    0.09
    phy
    0.09
    严ç¦ģ
    0.09
    森æŀĹ
    0.08
    æĢ¼
    0.08
     hover
    0.08
    елÑĮ
    0.08
    èµ°å»Ĭ
    0.08
    Activations Density 0.661%

    No Known Activations