© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64037
    Prev
    Next
    INDEX
    Explanations

    fungal infection aspergillosis

    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
    Negative Logits
    åѦåĪ°
    -0.10
    irate
    -0.10
    åijĬè¯ī大家
    -0.10
    å¤ľéĩĮ
    -0.10
    ä¸Ģå¤ľ
    -0.10
    æ½į
    -0.09
    çĻĥ
    -0.09
    åĵĪå°Ķ
    -0.09
    POSITION
    -0.09
    åĴĮæĬĢæľ¯
    -0.09
    POSITIVE LOGITS
    çŁ³å®¶
    0.09
    OMP
    0.09
    åIJĮå¿ĥ
    0.09
    gp
    0.08
    ilent
    0.08
     Aren
    0.08
    (Op
    0.08
    éĴ½
    0.08
    uur
    0.08
    .conf
    0.08
    Activations Density 0.528%

    No Known Activations