© 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. 32742
    Prev
    Next
    INDEX
    Explanations

    states of being or silence

    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
    çļĦåŃĺåľ¨
    -0.09
     pis
    -0.09
    é£İæĥħ
    -0.09
    aset
    -0.08
    aland
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    lef
    -0.08
    æľĭåıĭ们
    -0.08
    绸
    -0.08
    ä¸įæĺĵ
    -0.08
    POSITIVE LOGITS
    åħį
    0.09
     Plat
    0.09
     Deposit
    0.09
    uve
    0.08
    ä¸Ģä¼ļ
    0.08
    éŃģ
    0.08
    å¼Ń
    0.08
    ä¸Ģä¼ļåĦ¿
    0.08
    çĿ¬
    0.08
    emy
    0.08
    Activations Density 0.007%

    No Known Activations