© 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. 50301
    Prev
    Next
    INDEX
    Explanations

    reason or reasons

    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
    漪
    -0.10
    æĦŁè§īåĪ°
    -0.09
    çĤ¹å¤ļ
    -0.09
    ä¸įå®ļ
    -0.08
    èĦ²
    -0.08
    åį¦
    -0.08
     gem
    -0.08
    çĥĤ
    -0.08
    à¸Ńำà¸Ļาà¸Ī
    -0.08
    çİ¥
    -0.08
    POSITIVE LOGITS
    æĿ¥åĪ°
    0.15
    æĿ¥è¿ĻéĩĮ
    0.15
    èĢĮæĿ¥
    0.14
    æĺ¯ä¸ºäºĨ
    0.14
    è¿ĽæĿ¥
    0.13
    å°±æĺ¯ä¸ºäºĨ
    0.13
    åīįæĿ¥
    0.12
    åİŁåĽłä¹ĭä¸Ģ
    0.11
    æĿ¥æī¾
    0.11
    赶æĿ¥
    0.11
    Activations Density 0.076%

    No Known Activations