© 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. 3657
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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¸įå¿į
    -0.11
    åĪĿä¸ī
    -0.09
    åĵį
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    声åĵį
    -0.09
    segue
    -0.09
    人工
    -0.09
    带çĿĢ
    -0.09
    DÄ°
    -0.09
    aiser
    -0.08
    POSITIVE LOGITS
    çı£
    0.11
    æ°´çĶµ
    0.10
    åĤ¬
    0.10
    urst
    0.09
    çļĪ
    0.09
     run
    0.09
    éĹº
    0.08
     real
    0.08
    æľĿéĺ³
    0.08
    eree
    0.08
    Activations Density 0.140%

    No Known Activations