© 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. 34460
    Prev
    Next
    INDEX
    Explanations

    cameras and zoom lenses

    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
    为ä¹ĭ
    -0.09
    æģ¯æģ¯
    -0.08
    æİĪ
    -0.08
     re
    -0.08
    каÑĤ
    -0.08
    éĽ¹
    -0.08
    èĤ¤
    -0.08
    èĬĿ
    -0.08
    åIJ
    -0.07
    emen
    -0.07
    POSITIVE LOGITS
    æķ°çłģ
    0.11
    erable
    0.10
    ä¸ĢéĶ®
    0.10
    çĮ´
    0.09
    lectual
    0.09
    ë°±
    0.09
    Slim
    0.09
    ữ
    0.09
    LOUR
    0.09
    plode
    0.09
    Activations Density 0.014%

    No Known Activations