© 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. 48779
    Prev
    Next
    INDEX
    Explanations

    currents and electrical properties

    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
    pty
    -0.10
    inton
    -0.10
     scal
    -0.09
    åİĨåı²ä¸Ĭ
    -0.09
    OSH
    -0.08
    üs
    -0.08
    çIJ¨
    -0.08
    late
    -0.08
    éĢĤ度
    -0.08
    èĭŀ
    -0.08
    POSITIVE LOGITS
    íĿIJ
    0.10
    ìķĶ
    0.10
    æµģåĬ¨
    0.10
    ocale
    0.09
     Rivers
    0.09
    æµģåIJij
    0.09
    ãĥĻãĥ¼ãĤ¹
    0.09
    æ³»
    0.09
     Basin
    0.09
    eya
    0.09
    Activations Density 0.071%

    No Known Activations