© 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. 12270
    Prev
    Next
    INDEX
    Explanations

    electoral college, delegates, results, invention, blog, copyright

    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
    lian
    -0.09
    æ²ĥå°Ķ
    -0.09
    illon
    -0.08
    obra
    -0.08
    èĬľ
    -0.08
    åĨįéĢł
    -0.08
    _OVERFLOW
    -0.08
    æīĭæĮģ
    -0.08
    人çĶŁ
    -0.08
    ativo
    -0.08
    POSITIVE LOGITS
    ibu
    0.10
    нÑıÑĤ
    0.10
    å§Ķ
    0.09
    ÄĻd
    0.09
    ensa
    0.09
    顺åºĶ
    0.09
    /vendors
    0.09
    åĽ½åĬ¡
    0.08
    æ²ħ
    0.08
    èħ¾
    0.08
    Activations Density 0.022%

    No Known Activations