© 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. 33106
    Prev
    Next
    INDEX
    Explanations

    damage and injuries

    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
    èĤ¥
    -0.10
    å¾Īæ£Ĵ
    -0.09
    åłĩ
    -0.09
    ä¹ħäºĨ
    -0.09
    uters
    -0.09
    顶
    -0.08
    à®ľ
    -0.08
    isle
    -0.08
    ICE
    -0.08
     withheld
    -0.08
    POSITIVE LOGITS
    à¸Īาà¸ģà¸ģาร
    0.10
    éĤij
    0.10
    ä¸ĢèĦ¸
    0.10
    èĦ¸ä¸Ĭ
    0.10
    累累
    0.10
    æĿ¥èĩªäºİ
    0.10
     лиÑĨа
    0.10
    éģį
    0.09
    -faced
    0.09
    æĿ¥èĩª
    0.09
    Activations Density 0.107%

    No Known Activations