© 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. 20932
    Prev
    Next
    INDEX
    Explanations

    left or right

    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
    åĴ¸
    -0.11
    ailles
    -0.08
    dle
    -0.08
    UME
    -0.08
    ãĤ¿ãĤ¤ãĥł
    -0.08
    .getWindow
    -0.08
    èĥ¤
    -0.08
    'post
    -0.08
    Navigator
    -0.08
    åĮħ容
    -0.08
    POSITIVE LOGITS
    家åĽŃ
    0.10
    ä¸įä¹ı
    0.09
    æľīä¸įå°ij
    0.09
    ä½ľä¸ºä¸ĢåIJį
    0.09
    çī¢åĽºæłijç«ĭ
    0.08
    ç»ĻæĤ¨
    0.08
    çļĦ女åĦ¿
    0.08
    Recovered
    0.08
    èµĦ
    0.08
    .CO
    0.08
    Activations Density 0.015%

    No Known Activations