© 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. 5075
    Prev
    Next
    INDEX
    Explanations

    power, backup, standby, call

    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
    ne
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    æļĤæŶ
    -0.08
    ä»Ĭ
    -0.08
    mentor
    -0.08
    éªIJ
    -0.08
    öh
    -0.08
    æĹ©æľŁ
    -0.08
    åĪĿ次
    -0.08
    sci
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħ
    0.10
    iges
    0.10
    hev
    0.09
     sÃłng
    0.09
    -election
    0.09
    æľĽçĿĢ
    0.08
    åŁİéķĩåĮĸ
    0.08
    emo
    0.08
    æĹ¥çĶµ
    0.08
    ijing
    0.08
    Activations Density 0.010%

    No Known Activations