© 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. 40244
    Prev
    Next
    INDEX
    Explanations

    kne, ne, net

    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
    aceous
    -0.10
    é«¡
    -0.09
    rous
    -0.09
    overn
    -0.08
    [
    -0.08
     bạc
    -0.08
    ç¬ijäºĨ
    -0.08
    posite
    -0.08
    ael
    -0.08
    ä»ħä¾Ľ
    -0.08
    POSITIVE LOGITS
    è´°
    0.09
    ree
    0.09
    tgt
    0.08
    åĦ¿
    0.08
     Mein
    0.08
    åıįæŃ£
    0.08
    avic
    0.08
    éģķãģĦ
    0.08
    èįīåĿª
    0.08
    äºĨä¸Ģä¼ļ
    0.08
    Activations Density 0.002%

    No Known Activations