© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52018
    Prev
    Next
    INDEX
    Explanations

    website and site related terms

    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
    vio
    -0.10
    addir
    -0.09
    uib
    -0.09
    yte
    -0.08
    æĬ±
    -0.08
    addin
    -0.08
    æł¡
    -0.08
    Lic
    -0.08
    åĨ
    -0.08
    itive
    -0.08
    POSITIVE LOGITS
    мед
    0.10
    èħ³
    0.10
    è·µ
    0.10
    èĦļ
    0.09
    äºı
    0.09
    ä¼´ä¾£
    0.08
    çļĦä¿¡æģ¯
    0.08
    SDK
    0.08
    taÅŁ
    0.08
    è¿IJèIJ¥åķĨ
    0.08
    Activations Density 0.009%

    No Known Activations