© 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. 57807
    Prev
    Next
    INDEX
    Explanations

    US vote

    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
    åķ¤
    -0.11
    ä¸ĩ象
    -0.09
    æĹĦ
    -0.09
    ç«ŀ
    -0.09
    èĬij
    -0.08
    çĹĴ
    -0.08
    positories
    -0.08
     биз
    -0.08
    窸
    -0.08
    èĸĩ
    -0.08
    POSITIVE LOGITS
    opathy
    0.09
    é»į
    0.09
     homeschool
    0.09
    éĿŀ常å¤ļçļĦ
    0.08
    walker
    0.08
    lector
    0.08
    æķĻèĤ²æķĻåѦ
    0.08
    ModelIndex
    0.08
    /op
    0.08
    æĪij认为
    0.08
    Activations Density 0.347%

    No Known Activations