© 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. 31549
    Prev
    Next
    INDEX
    Explanations

    conditions are met

    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
     огÑĢаниÑĩен
    -0.10
    ukt
    -0.09
    欢è¿İæĤ¨
    -0.09
    èµ·æŃ¥
    -0.09
     unus
    -0.09
    æĦıåIJij
    -0.09
    èݪ
    -0.09
    çĻŀ
    -0.09
    uhn
    -0.09
    ãĤĴéĽĨ
    -0.08
    POSITIVE LOGITS
    å±¥è¡Į
    0.13
     met
    0.12
     fulfilled
    0.12
     fulfillment
    0.10
    å¾Ĺ以
    0.10
    æ®·
    0.09
    met
    0.09
    ulfilled
    0.09
    满足
    0.09
     fulfill
    0.09
    Activations Density 0.113%

    No Known Activations