© 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. 33490
    Prev
    Next
    INDEX
    Explanations

    cleanup effort

    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
    åIJİæİĴ
    -0.09
    åºŁ
    -0.09
    æĸ°åħ´
    -0.08
    麸
    -0.08
    æĹłæĦı
    -0.08
     Frederick
    -0.08
    é¢Ħå¤ĩ
    -0.08
     bang
    -0.08
    iner
    -0.08
    çīĪæĿĥæīĢæľī
    -0.08
    POSITIVE LOGITS
    奥巴马
    0.10
    éķ¿æķĪ
    0.10
    æı©
    0.10
    æĨĶ
    0.10
    ozo
    0.10
    çģ¶
    0.10
    èĪªè¡Į
    0.09
    褰
    0.09
    å®ĺæĸ¹å¾®åįļ
    0.09
    Invoker
    0.09
    Activations Density 0.021%

    No Known Activations