© 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. 7139
    Prev
    Next
    INDEX
    Explanations

    the word picture

    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
    uce
    -0.09
    echa
    -0.09
    icks
    -0.08
    CastException
    -0.08
    ynes
    -0.08
    erie
    -0.08
    è¿ĩå¤ļ
    -0.08
    زÙĬ
    -0.08
    们çļĦ
    -0.08
    listed
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¹ħ
    0.09
     darn
    0.09
    aban
    0.08
     Dunn
    0.08
    ONY
    0.08
    岿
    0.08
    nı
    0.08
    ÐIJÐĿ
    0.08
    à¹ĭ
    0.08
    rary
    0.08
    Activations Density 0.033%

    No Known Activations