© 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. 34559
    Prev
    Next
    INDEX
    Explanations

    paradox

    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
    apping
    -0.09
    å»ĵ
    -0.09
    ắn
    -0.08
    abouts
    -0.08
    aning
    -0.08
    enge
    -0.08
    æĶ¯æĮģåĬĽåº¦
    -0.08
    owed
    -0.08
     ×Ķ׼
    -0.08
    ä¸Ģå°ı
    -0.08
    POSITIVE LOGITS
    ical
    0.14
    æĢ§çļĦ
    0.13
    ously
    0.11
    æīĢåľ¨
    0.10
    ä¸įæĪIJ
    0.10
    edException
    0.10
    ICAL
    0.10
    icity
    0.10
    å¤Ħå¢ĥ
    0.10
    omic
    0.10
    Activations Density 0.012%

    No Known Activations