© 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. 6307
    Prev
    Next
    INDEX
    Explanations

    take in

    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
    AccessException
    -0.09
    缦
    -0.09
    åĩºåħ¥
    -0.09
    åłª
    -0.09
    OOM
    -0.09
    pling
    -0.08
    _PHP
    -0.08
    tte
    -0.08
    以æĿ¥
    -0.08
    庵
    -0.08
    POSITIVE LOGITS
    ç¾½æ¯Ľ
    0.09
    çĺª
    0.08
    大èĩªçĦ¶
    0.08
    æ¶ķ
    0.08
    ionate
    0.08
     iÅŁaret
    0.08
    radius
    0.08
    æīĭå·¥
    0.08
    lus
    0.08
    éħį
    0.08
    Activations Density 0.005%

    No Known Activations