© 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. 49984
    Prev
    Next
    INDEX
    Explanations

    hands behind backs

    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
    éĴĵé±¼
    -0.09
    رÙĬ
    -0.09
    è°±
    -0.09
    ç¬ij
    -0.09
    uni
    -0.09
    ä¸įæľį
    -0.09
    packing
    -0.09
     __________________↵↵
    -0.09
    çĶ¸
    -0.09
    èĩªæ²»
    -0.09
    POSITIVE LOGITS
    åıĮæīĭ
    0.25
     hands
    0.20
     Hands
    0.18
    hands
    0.17
    Hands
    0.17
    æīĭä¸Ĭ
    0.16
    æīĭä¸Ń
    0.15
     ÑĢÑĥк
    0.14
     manos
    0.12
    æīĭéĩĮ
    0.12
    Activations Density 0.033%

    No Known Activations