© 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. 62355
    Prev
    Next
    INDEX
    Explanations

    brand names

    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
    éĿ©
    -0.13
    ool
    -0.10
    人家
    -0.10
    æīĢåľ¨çļĦ
    -0.09
    åĨ·åĨ·
    -0.09
    轩
    -0.09
    ä¸Ńåħ±
    -0.08
    assy
    -0.08
    èĢ½
    -0.08
    羿
    -0.08
    POSITIVE LOGITS
    åħ¬åı¸çļĦ
    0.11
    æĹĹä¸ĭçļĦ
    0.10
     Corporation
    0.10
    çļĦä¸ľè¥¿
    0.09
    -sponsored
    0.09
    æĹĹä¸ĭ
    0.09
    æݨåĩºçļĦ
    0.09
    ä¾ĽåĽ¾
    0.09
     corporation
    0.09
    UES
    0.08
    Activations Density 0.215%

    No Known Activations