© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8182
    Prev
    Next
    INDEX
    Explanations

    action and control commands

    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
    交éĶĻ
    -0.10
    çĽ¸å¯¹è¾ĥ
    -0.09
    伸åĩº
    -0.09
    è¯ł
    -0.08
    uja
    -0.08
    èĢĹ
    -0.08
    åľ¨è¿ĩ渡
    -0.08
    èŀ³
    -0.08
    å°ĨæĮģç»Ń
    -0.08
    è´Łèį·
    -0.08
    POSITIVE LOGITS
    å°¼æĸ¯
    0.10
    oggle
    0.09
    _TOGGLE
    0.09
    toggleClass
    0.08
    ëħIJ
    0.08
    .Diagnostics
    0.08
    åĤ¬
    0.08
    .toggle
    0.08
    globals
    0.08
    ä¿Ŀæļĸ
    0.08
    Activations Density 0.160%

    No Known Activations