© 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. 58014
    Prev
    Next
    INDEX
    Explanations

    Names and places

    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
    bis
    -0.10
    å¥ī
    -0.09
    _splits
    -0.09
    è¿Ļåĩłä¸ª
    -0.09
     Hastings
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    ä¸Ńæĸ°
    -0.09
    /includes
    -0.08
    oran
    -0.08
    lector
    -0.08
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.12
    ä¹Łä¸įä¾ĭå¤ĸ
    0.12
    éĽħ
    0.10
    ä¸İæѤ
    0.09
    çĦī
    0.09
    为åħ¶
    0.09
    éĻ¤å¤ĸ
    0.08
    çĹ
    0.08
    adel
    0.08
    cke
    0.08
    Activations Density 1.134%

    No Known Activations