© 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. 56413
    Prev
    Next
    INDEX
    Explanations

    open or opening

    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
    æĵį
    -0.10
    UEL
    -0.09
    åĵ®
    -0.09
    лÑij
    -0.08
    ntax
    -0.08
    .mas
    -0.08
    å¾½
    -0.08
    ONY
    -0.08
    访
    -0.08
    боÑĤ
    -0.08
    POSITIVE LOGITS
    çİ©ç¬ij
    0.14
    çľ¼çķĮ
    0.14
    æĸ°å±ĢéĿ¢
    0.13
    大éŨ
    0.13
    åºıå¹ķ
    0.12
    æīī
    0.12
    à¹Ģà¸ľà¸¢
    0.12
    æĸ°æł¼å±Ģ
    0.12
     doors
    0.12
    æķŀ
    0.11
    Activations Density 0.177%

    No Known Activations