© 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. 27488
    Prev
    Next
    INDEX
    Explanations

    supposed to be

    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
    åīįæīĢ
    -0.10
    éħ¿
    -0.09
    Measured
    -0.09
    soever
    -0.09
    è¾Ľåĭ¤
    -0.09
    éĿ
    -0.09
    dio
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    åķ¬
    -0.09
     taped
    -0.08
    POSITIVE LOGITS
    alled
    0.10
    浪漫
    0.10
    ä»Ķç»Ĩ
    0.09
    æį®æѤ
    0.09
    -Feb
    0.09
    磾
    0.09
     supposed
    0.09
    严å¯Ĩ
    0.09
    è¿ĽæĿ¥
    0.08
    arb
    0.08
    Activations Density 0.071%

    No Known Activations