© 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. 1641
    Prev
    Next
    INDEX
    Explanations

    crossroads of opportunity

    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
    é»ĺå¥ij
    -0.10
    æľīåĬĽ
    -0.09
    裸
    -0.09
    ëł¹
    -0.09
    REN
    -0.08
    ision
    -0.08
    à¸ģระ
    -0.08
     Valencia
    -0.08
    encies
    -0.08
    çĽĪ
    -0.08
    POSITIVE LOGITS
    éĢĨè¢Ń
    0.11
    翻身
    0.11
    çĶ«
    0.11
    夢
    0.10
    æĻĭåįĩ
    0.10
    ç½®ä¸ļ
    0.10
    éĿł
    0.10
    梦
    0.10
    蹿
    0.10
    åIJijä¸Ĭ
    0.09
    Activations Density 0.077%

    No Known Activations