© 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. 59341
    Prev
    Next
    INDEX
    Explanations

    image size or quality

    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
    URN
    -0.09
    ç«¿
    -0.09
    æĭŃ
    -0.09
    å½ķ
    -0.09
    /documentation
    -0.09
    å½ķéŁ³
    -0.09
    æį¡
    -0.08
    .ZERO
    -0.08
    ipy
    -0.08
    _STARTED
    -0.08
    POSITIVE LOGITS
     enlargement
    0.11
    æĶ¾å¤§
    0.11
     enlarge
    0.10
    ãģĭãģĦ
    0.09
    endar
    0.09
    æݥ管
    0.09
     images
    0.09
    éĶ²
    0.09
    ä¸Ģå¹ħ
    0.09
    çľ¼çľĭ
    0.09
    Activations Density 0.075%

    No Known Activations