© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63834
    Prev
    Next
    INDEX
    Explanations

    prefix or suffix

    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
    à¸ģระà¸ļ
    -0.08
    ioned
    -0.08
    nth
    -0.08
    à´²
    -0.08
    anna
    -0.08
    åľ¨æĪijçļĦ
    -0.08
    è°©
    -0.08
    à¸Ĭà¸Ļ
    -0.08
    æĶ¶ç¼©
    -0.08
    modulo
    -0.08
    POSITIVE LOGITS
    ä¿Ł
    0.10
    èĢĮåIJİ
    0.10
    建æĪIJåIJİ
    0.09
    ä¸Ģç»Ħ
    0.09
    èѦåĬ¡
    0.08
    éħįå¥Ĺ
    0.08
    廨
    0.08
    桦
    0.08
    对çħ§
    0.08
    uala
    0.08
    Activations Density 0.029%

    No Known Activations