© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    refrigerant and refrigeration

    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
     benef
    -0.10
    éľĸ
    -0.09
    _rest
    -0.09
    çķĻä¸ĭæĿ¥
    -0.09
    éķ
    -0.09
    红åĪ©
    -0.09
    adic
    -0.09
    天ä¸ĭ
    -0.09
    çIJ¬
    -0.08
    ä¸ĢåľĪ
    -0.08
    POSITIVE LOGITS
     refriger
    0.10
    éĢĴ
    0.09
    åĪ¶åĨ·
    0.08
    è²Ķ
    0.08
    crit
    0.08
    顽强
    0.08
    estate
    0.08
    好å¥ĩ
    0.08
    æ³ķå®ļ
    0.08
    æĮģæľī
    0.08
    Activations Density 0.069%

    No Known Activations