© 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. 37522
    Prev
    Next
    INDEX
    Explanations

    about topics and questions

    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
    æĪijçľĭ
    -0.11
    OLA
    -0.10
    rock
    -0.10
    ç½ijåıĭè¯Ħ论
    -0.10
    eri
    -0.10
    ayah
    -0.10
     обÑĢазом
    -0.09
     Engl
    -0.09
    ophil
    -0.09
    bud
    -0.09
    POSITIVE LOGITS
    ÙĪاÙĨ
    0.11
     طرÙĬÙĤ
    0.11
    /on
    0.10
    ç§įç§į
    0.10
    ting
    0.10
    doi
    0.10
    ราว
    0.10
    brush
    0.10
    åį°åıij
    0.10
    ation
    0.10
    Activations Density 0.112%

    No Known Activations