© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38489
    Prev
    Next
    INDEX
    Explanations

    District Court Appellant Petitioner

    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
    åĬ¬
    -0.10
    åĨł
    -0.10
    ä¸Ģ度
    -0.09
    è¡į
    -0.09
    æºľ
    -0.09
    oscope
    -0.09
    çĿ£å¯¼
    -0.09
    æĴŃ
    -0.08
     DAG
    -0.08
    éĹªçĥģ
    -0.08
    POSITIVE LOGITS
    å²ŃåįĹ
    0.15
    åľ¨å¹¿å·ŀ
    0.12
    广å·ŀ
    0.10
    icl
    0.09
     Eduardo
    0.09
    éĽ¢
    0.09
    å²Ń
    0.09
    åĽ½æ°ij
    0.09
    tone
    0.08
     Lisbon
    0.08
    Activations Density 0.057%

    No Known Activations