© 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. 60577
    Prev
    Next
    INDEX
    Explanations

    spa, holidays, VPN

    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
    Negative Logits
    ives
    -0.13
    oplay
    -0.10
    ality
    -0.10
    è¾ĥ好
    -0.10
    zelf
    -0.09
    aires
    -0.09
    naire
    -0.09
    ваÑĢ
    -0.09
    pute
    -0.09
    utf
    -0.09
    POSITIVE LOGITS
    åIJģ
    0.10
    人士
    0.09
    åľ°åĿª
    0.09
    ç¯ģ
    0.09
    olu
    0.09
    BED
    0.09
    å´Ĩ
    0.09
    -rock
    0.08
    å¸ı
    0.08
    ä½ķå¤Ħ
    0.08
    Activations Density 0.005%

    No Known Activations