© 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. 60918
    Prev
    Next
    INDEX
    Explanations

    fresh perspective or new idea

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åīįä¸ĸ
    -0.10
    åºŁå¼ĥ
    -0.09
    夫人
    -0.09
    éļľ
    -0.09
    éºŁ
    -0.09
    æĥ¹
    -0.09
    IZER
    -0.08
    åĮ¿åIJį
    -0.08
    frag
    -0.08
    éĻ·éĺ±
    -0.08
    POSITIVE LOGITS
     Fresh
    0.12
    æĸ°é²ľ
    0.12
     fresh
    0.11
    Fresh
    0.11
    é²ľ
    0.10
     freshness
    0.09
    erties
    0.09
    é®®
    0.09
     renewal
    0.09
    fresh
    0.09
    Activations Density 0.021%

    No Known Activations