© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20417
    Prev
    Next
    INDEX
    Explanations

    viral diseases and syndromes

    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
    è¿ĩæĿ¥
    -0.10
    çªĿ
    -0.08
    ä¼ĺ
    -0.08
    .blank
    -0.08
    ighthouse
    -0.07
    blank
    -0.07
    äge
    -0.07
    èı½
    -0.07
    æķ¦
    -0.07
     repetitions
    -0.07
    POSITIVE LOGITS
    é¢Ĭ
    0.11
    ÑĦи
    0.10
    åħ¨éĿ¢åıijå±ķ
    0.09
     Lev
    0.09
    车载
    0.09
    èĭ¦æģ¼
    0.09
    _RB
    0.09
    ymm
    0.09
    èĪģ
    0.09
    èµī
    0.09
    Activations Density 0.214%

    No Known Activations