© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    understand / remember / what

    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
    erot
    -0.11
    è¦ģç´§
    -0.10
    è¿ĺä¸įæĺ¯
    -0.09
    å·²ç»ıæľīäºĨ
    -0.09
    为ä¸Ńå¿ĥ
    -0.09
    plates
    -0.09
    brane
    -0.09
     ÑĥвеÑĢен
    -0.09
    èĩªä¿¡
    -0.09
    å·²ç»ıå¼Ģå§ĭ
    -0.08
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.13
     experience
    0.12
     Experience
    0.11
    ä½ĵä¼ļ
    0.11
    ç»ıéªĮ
    0.11
    ç»ıåİĨè¿ĩ
    0.11
    ä½ĵä¼ļåĪ°
    0.10
    Experience
    0.10
    çļĦç»ıéªĮ
    0.10
    çĶ¨æĪ·ä½ĵéªĮ
    0.10
    Activations Density 0.067%

    No Known Activations