© 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. 6635
    Prev
    Next
    INDEX
    Explanations

    medical conditions and failures

    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
    ä¸įåıĬ
    -0.10
    ç£Ķ
    -0.08
    æ¼±
    -0.08
     dÄ±ÅŁÄ±
    -0.08
    æĩ·
    -0.08
    æĺıè¿·
    -0.08
    ä¸įæŃ»
    -0.08
    eming
    -0.08
    à¹īà¸ĩ
    -0.08
    æĿ¥æī¾
    -0.08
    POSITIVE LOGITS
    åĮª
    0.09
    å¹²
    0.09
    OTS
    0.09
    ãĥł
    0.09
    CTR
    0.09
    ran
    0.08
    çĩĥ
    0.08
    èŀºæĹĭ
    0.08
    éĿ
    0.08
    å¬ī
    0.08
    Activations Density 0.012%

    No Known Activations