© 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. 47491
    Prev
    Next
    INDEX
    Explanations

    available

    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
    è¥Ħ
    -0.12
    åĪĨæĺİ
    -0.10
    VICE
    -0.09
    æĹ©æĻļ
    -0.09
    æļ´éľ²
    -0.09
    æ³®
    -0.09
    edly
    -0.09
    pad
    -0.09
    éĻ¤éĿŀ
    -0.09
     Roads
    -0.08
    POSITIVE LOGITS
    ughs
    0.08
    çŀ»
    0.08
    è±Ĩ
    0.08
    assel
    0.08
    .blob
    0.08
    ë¡ľìĦľ
    0.08
    ottom
    0.08
    å½ĵä½ľ
    0.08
    GLOBALS
    0.07
    Nit
    0.07
    Activations Density 0.036%

    No Known Activations