© 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. 3666
    Prev
    Next
    INDEX
    Explanations

    mitochondrial

    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
    عاد
    -0.10
    otate
    -0.10
    çī©æµģä¼ģä¸ļ
    -0.09
    åĬ²
    -0.09
    ä¸į代表
    -0.09
    æİĴè¡Į
    -0.09
    empt
    -0.09
     gim
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    æľ¯
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.11
    sis
    0.09
    IDS
    0.08
    IDI
    0.08
    ä¸ŃçļĦ
    0.08
    èĭ´
    0.08
     Castillo
    0.08
    acci
    0.08
    ä¸ĬçļĦ
    0.08
    éĩĮçļĦ
    0.08
    Activations Density 0.425%

    No Known Activations