© 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. 55553
    Prev
    Next
    INDEX
    Explanations

    politicizing or political issue

    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
    Track
    -0.10
    éŁŃ
    -0.09
    вал
    -0.09
    çIJĨ论ä¸Ĭ
    -0.09
    è´¢
    -0.09
    åģ¥
    -0.09
     McL
    -0.09
    .setTo
    -0.08
    .getMethod
    -0.08
    çļĦæł¸å¿ĥ
    -0.08
    POSITIVE LOGITS
    æĶ¿æ²»
    0.09
    RH
    0.09
    ä¹ĭ举
    0.08
    æĬ¤çħ§
    0.08
    åĺĺ
    0.08
    /utility
    0.08
    ä¸ĵ享
    0.08
    äºĨäºĽ
    0.08
    çİ°è´§
    0.08
    çĶ¨éĢĶ
    0.08
    Activations Density 0.024%

    No Known Activations