© 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. 20823
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    -0.12
    ê²ģ
    -0.09
    าà¸ĩ
    -0.09
    ENTE
    -0.08
    ities
    -0.08
    odo
    -0.08
    áŀĽ
    -0.08
    SELF
    -0.08
    pll
    -0.08
    isher
    -0.07
    POSITIVE LOGITS
    对æİ¥
    0.10
    ogue
    0.10
    opi
    0.09
    apy
    0.09
    룬
    0.09
    çIJĨ解åĴĮ
    0.08
    æĪIJåĬŁä¸¾åĬŀ
    0.08
    rance
    0.08
    æĻ¨æĬ¥
    0.08
    oser
    0.08
    Activations Density 0.299%

    No Known Activations