© 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. 61271
    Prev
    Next
    INDEX
    Explanations

    official ceremony and protocol

    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
    emp
    -0.09
    pton
    -0.09
     moisture
    -0.08
    éĹ®éĹ®
    -0.08
    夺
    -0.08
     arbitrary
    -0.08
    èĸĦå¼±
    -0.08
    opic
    -0.08
     conjug
    -0.07
    ãĤ¸ãĥ¥
    -0.07
    POSITIVE LOGITS
    éļĨéĩį
    0.15
    åĩºå¸Ń
    0.11
    çĭIJ
    0.11
    éļĨéĩį举è¡Į
    0.11
    åľºåIJĪ
    0.11
    åģķ
    0.10
    礼仪
    0.10
    御
    0.10
    è¾Ĥ
    0.10
    礼
    0.10
    Activations Density 0.113%

    No Known Activations