© 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. 49030
    Prev
    Next
    INDEX
    Explanations

    aviation terms

    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
    ses
    -0.11
    sWith
    -0.09
    åŀ£
    -0.09
    acting
    -0.09
    åĵģ
    -0.09
    uplic
    -0.09
    å¸ļ
    -0.09
    éĺµåľ°
    -0.08
    amp
    -0.08
    ür
    -0.08
    POSITIVE LOGITS
    沫
    0.10
    iero
    0.09
    -themed
    0.08
     buffs
    0.08
    ics
    0.08
    StateChanged
    0.08
    terminated
    0.08
    ج
    0.08
    ä¿Ŀåģ¥
    0.08
    åı²ä¸Ĭ
    0.08
    Activations Density 0.012%

    No Known Activations