© 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. 6492
    Prev
    Next
    INDEX
    Explanations

    message broadcasting channels

    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
    大æĸ¹
    -0.10
    èĭ±éĽĦ
    -0.09
    纵
    -0.09
     Cooler
    -0.09
    é£İè²Į
    -0.09
    _Adjust
    -0.09
    ä¸ĭæīĭ
    -0.09
    ÑĤелÑĮ
    -0.08
    çĶ¨æĪ·ä½ĵéªĮ
    -0.08
    elsey
    -0.08
    POSITIVE LOGITS
     events
    0.10
     наÑĢ
    0.09
    éĢļéģĵ
    0.09
    æģ¯
    0.09
    eventName
    0.09
    çĽijåIJ¬
    0.09
     topic
    0.09
     channel
    0.09
    äºĭ件
    0.09
    çŃīåĢĻ
    0.09
    Activations Density 0.398%

    No Known Activations