© 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. 11616
    Prev
    Next
    INDEX
    Explanations

    introductions to people or groups

    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
    æīĵå¾Ĺ
    -0.09
    ÑijÑĢ
    -0.09
    å¼ķæĿ¥
    -0.09
    æµģè¡Į
    -0.08
    iday
    -0.08
    ç°Ł
    -0.08
    å°ıåŃIJ
    -0.08
    nest
    -0.08
    åı¬éĽĨ
    -0.08
     gov
    -0.08
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.18
     faces
    0.14
     face
    0.14
    éĿ¢å¯¹éĿ¢
    0.13
    å§ĵåIJį
    0.13
    -face
    0.13
    çĨŁæĤī
    0.13
    认è¯Ĩ
    0.13
    è§ģéĿ¢
    0.13
    缸è¯Ĩ
    0.13
    Activations Density 0.043%

    No Known Activations