© 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. 50119
    Prev
    Next
    INDEX
    Explanations

    hand, forearm, mouse, or osteoarthritis

    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
    æĻ¯å¾·
    -0.10
    ãĤĴä¸İãģĪ
    -0.09
    èĦī
    -0.09
    æīĴ
    -0.09
    èĥ³èĨĬ
    -0.08
    èĦĪ
    -0.08
    ä¸ĭå·´
    -0.08
    èĢ³æľµ
    -0.08
    åħ¢
    -0.08
     ÑĢÑĥк
    -0.08
    POSITIVE LOGITS
    åı·ç§°
    0.11
    翳
    0.10
    ooter
    0.10
    æĹ©æĹ©
    0.10
    æĹ©å°±
    0.09
    饲æĸĻ
    0.09
    迷人
    0.09
    à¹ĥ
    0.09
    åĨħåľ°
    0.09
    itis
    0.09
    Activations Density 0.082%

    No Known Activations