© 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. 18157
    Prev
    Next
    INDEX
    Explanations

    flying aircraft

    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
    еÑĢÑĮ
    -0.11
    åµĺ
    -0.10
    ç±´
    -0.09
    ä½ĵèĤ²åľº
    -0.09
    à¸ģระà¸Ĺ
    -0.09
    çľ¼éĩĮ
    -0.09
    ively
    -0.09
    读书
    -0.09
    æīĭä¸Ń
    -0.09
    æıĽ
    -0.09
    POSITIVE LOGITS
    çķ´
    0.09
    éĢıæĺİ
    0.09
    èĪ¸
    0.09
    åij
    0.09
    -offs
    0.08
    mph
    0.08
    gear
    0.08
    cape
    0.08
    wed
    0.08
    ogs
    0.08
    Activations Density 0.023%

    No Known Activations