© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20450
    Prev
    Next
    INDEX
    Explanations

    SpriteKit, Pygame, game code

    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
    çĢijå¸ĥ
    -0.08
     phó
    -0.08
    Automation
    -0.08
    æİ´
    -0.08
    æĹ·
    -0.08
    é¢ı
    -0.08
    _CTX
    -0.08
     diz
    -0.08
    Collapsed
    -0.08
    uhl
    -0.08
    POSITIVE LOGITS
    åĽº
    0.10
    è¿IJåĬ¨
    0.10
    .shapes
    0.10
     SimpleName
    0.09
    ieux
    0.09
     лÑĥÑĩ
    0.09
    Moved
    0.09
     Moved
    0.08
    移åĪ°
    0.08
    æĸ°æµªå¾®åįļ
    0.08
    Activations Density 0.480%

    No Known Activations