© 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. 610
    Prev
    Next
    INDEX
    Explanations

    course of development or evolution

    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
    æĭĽçīĮ
    -0.10
    æĮij
    -0.09
    çĥŃ
    -0.09
     Trav
    -0.09
     Tib
    -0.09
    trand
    -0.09
    èĮħ
    -0.08
    çĥŃçĪ±
    -0.08
    iser
    -0.08
     Perc
    -0.08
    POSITIVE LOGITS
    åıĺåĮĸ
    0.11
    èµ°åĬ¿
    0.11
    ucci
    0.11
    è¶ĭåĬ¿
    0.10
    è®ĬåĮĸ
    0.10
    è¿Ľå±ķæĥħåĨµ
    0.09
     fate
    0.09
    åıijå±ķè¶ĭåĬ¿
    0.09
    åķľ
    0.09
    OWL
    0.09
    Activations Density 0.172%

    No Known Activations