© 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. 22787
    Prev
    Next
    INDEX
    Explanations

    health care professional

    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
    éļıæŶéļıåľ°
    -0.11
    磨
    -0.09
    èĩªåĬ©
    -0.09
    _exact
    -0.08
    kus
    -0.08
     UIP
    -0.08
    Exact
    -0.08
    æĸŃ
    -0.08
    使çĶ¨æĿĥ
    -0.07
    éĺ´éĺ³
    -0.07
    POSITIVE LOGITS
    æŃ¤äºº
    0.09
    人士
    0.09
    人为
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
    å·¥ä½ľèĢħ
    0.09
    è´Łè´£äºº
    0.09
    åĵ²
    0.09
    afil
    0.09
    å·¥ä½ľäººåijĺ
    0.08
    çłĶåĪ¤
    0.08
    Activations Density 0.021%

    No Known Activations