© 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. 37492
    Prev
    Next
    INDEX
    Explanations

    external stimuli or conditions

    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
    èĩªå¾ĭ
    -0.11
    kir
    -0.10
    æ§Ľ
    -0.09
    ç¨Ķ
    -0.09
     Hoy
    -0.09
    åĪ·æĸ°
    -0.08
    elder
    -0.08
    深深çļĦ
    -0.08
    à¹Ģà¸Ļ
    -0.08
    greg
    -0.08
    POSITIVE LOGITS
    å¤ĸçķĮ
    0.33
    å¤ĸéĥ¨
    0.31
     external
    0.25
    å¤ĸéĿ¢
    0.23
     внеÑĪ
    0.21
    External
    0.21
    external
    0.21
     External
    0.20
    _external
    0.19
     outside
    0.18
    Activations Density 0.110%

    No Known Activations