© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54934
    Prev
    Next
    INDEX
    Explanations

    zip code or location

    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
    JOR
    -0.10
    anson
    -0.09
    ç¼¢
    -0.09
    каÑĢ
    -0.09
    stance
    -0.09
     ëĮĵê¸Ģ
    -0.09
    mob
    -0.09
    CEE
    -0.09
    .INSTANCE
    -0.09
    æѦ
    -0.09
    POSITIVE LOGITS
    太
    0.09
    ä»»ä½ķä¸Ģ个
    0.08
    åįı
    0.08
    lect
    0.08
     instead
    0.08
    _IS
    0.08
    åħ·ä½ĵ
    0.07
    æĸ¹åľĨ
    0.07
     keyed
    0.07
    ä»»ä½ķå½¢å¼ı
    0.07
    Activations Density 0.001%

    No Known Activations