© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19810
    Prev
    Next
    INDEX
    Explanations

    any kind

    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
    为广大
    -0.09
     vivo
    -0.08
    emic
    -0.08
    عÙĦÙĬ
    -0.08
    èĵ¬
    -0.08
    æķ¬è¯·
    -0.08
    åħ¨åijĺ
    -0.08
    横
    -0.08
    æīĭèħķ
    -0.08
    orn
    -0.08
    POSITIVE LOGITS
    æijĨåľ¨
    0.11
     Mature
    0.10
    ä½İä¸ĭ
    0.10
    æĪIJçĨŁ
    0.10
    inition
    0.10
    athing
    0.10
    icans
    0.09
    cratch
    0.09
    é©»
    0.08
    æĸĿ
    0.08
    Activations Density 0.116%

    No Known Activations