© 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. 21021
    Prev
    Next
    INDEX
    Explanations

    shades of colors

    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
    idad
    -0.10
    ihad
    -0.09
    ivity
    -0.09
     Stard
    -0.09
    Ãłng
    -0.09
    itaire
    -0.08
    ×ķת
    -0.08
    áĢĨ
    -0.08
     взглÑıд
    -0.08
    à¹Į
    -0.08
    POSITIVE LOGITS
    èļĤ
    0.12
    æģŃåĸľ
    0.11
    级以ä¸Ĭ
    0.10
    ocking
    0.10
    kick
    0.10
    ê¹Ķ
    0.09
    less
    0.09
    åºľ
    0.09
    uator
    0.09
    лем
    0.09
    Activations Density 0.008%

    No Known Activations