© 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. 18589
    Prev
    Next
    INDEX
    Explanations

    writing stories and characters

    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
     Sund
    -0.10
    主æµģ
    -0.10
    kir
    -0.10
    SES
    -0.09
    .pretty
    -0.09
    å¹»æĥ³
    -0.09
     mainstream
    -0.08
    imator
    -0.08
    æ²Ķ
    -0.08
    åĵĻ
    -0.08
    POSITIVE LOGITS
    çģµæĦŁ
    0.11
    æŀĦæĢĿ
    0.11
    åĨĻä¸ĭ
    0.11
    ç´łæĿIJ
    0.11
    åĨĻä½ľ
    0.10
    æıª
    0.10
    æĢĿè·¯
    0.10
    æĵİ
    0.09
    大纲
    0.09
     incorpor
    0.08
    Activations Density 0.062%

    No Known Activations