© 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. 63297
    Prev
    Next
    INDEX
    Explanations

    legislative acts

    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
    èĢĥçĶŁ
    -0.09
    avy
    -0.08
    /legal
    -0.08
     cust
    -0.08
    岸
    -0.08
    theme
    -0.08
    æĸ°åŁİ
    -0.08
    æį¢å±Ĭ
    -0.08
    æ¹ĸåĮº
    -0.08
    缴èĩ³
    -0.08
    POSITIVE LOGITS
     Act
    0.13
    æĿ¡ä¾ĭ
    0.10
    Act
    0.10
    管çIJĨæĿ¡ä¾ĭ
    0.10
    å®Ī
    0.10
    requ
    0.09
    年代
    0.09
    æ³ķæ¡Ī
    0.09
    laden
    0.09
    lke
    0.09
    Activations Density 0.099%

    No Known Activations