© 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. 26071
    Prev
    Next
    INDEX
    Explanations

    hiking

    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
    ities
    -0.12
    æľĢåIJİä¸Ģ次
    -0.10
    coni
    -0.09
    icer
    -0.09
     Ñģобой
    -0.09
    lie
    -0.09
    ikan
    -0.09
    hood
    -0.09
    nelle
    -0.09
    è¿ĩåī©
    -0.09
    POSITIVE LOGITS
    ernet
    0.10
    adem
    0.09
    eners
    0.09
    enden
    0.09
    ł
    0.08
    ê°Ŀ
    0.08
    OrCreate
    0.08
    éĢı
    0.08
    æ¤ħ
    0.08
    starter
    0.08
    Activations Density 0.005%

    No Known Activations