© 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. 53587
    Prev
    Next
    INDEX
    Explanations

    conservative politicians and parties

    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
    ç¢Ľ
    -0.10
    æĹłç§ģ
    -0.10
    ngo
    -0.10
    agement
    -0.09
    å¹ķåIJİ
    -0.09
    soles
    -0.09
    ä¼ī
    -0.09
    ä¸ĸ人
    -0.09
    çIJĨæĻº
    -0.09
    çļĦéĤ£ä¸Ģ
    -0.09
    POSITIVE LOGITS
    çīĽ
    0.10
    alar
    0.10
    iegel
    0.09
    ê¸Ī
    0.08
    chaft
    0.08
    们
    0.08
    å¥Ħ
    0.08
    士
    0.08
     ApiException
    0.08
    onder
    0.08
    Activations Density 0.010%

    No Known Activations