© 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. 33505
    Prev
    Next
    INDEX
    Explanations

    polite requests and gratitude

    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
     isp
    -0.09
    æľīå¾ħ
    -0.09
    lico
    -0.08
    浩
    -0.08
    溯
    -0.08
    cer
    -0.08
    clr
    -0.08
     ise
    -0.08
     Tau
    -0.08
    ä½łæĺ¯
    -0.08
    POSITIVE LOGITS
    å°½éĩı
    0.12
    好åIJĹ
    0.11
    çĤľ
    0.10
    ä¸įè¦ģåĨį
    0.10
    åŃĢ
    0.10
    æľĢ好ä¸įè¦ģ
    0.10
     Dwight
    0.09
    æĿĢæīĭ
    0.09
    æľĢ好æĺ¯
    0.09
    温馨
    0.09
    Activations Density 0.071%

    No Known Activations