© 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. 29593
    Prev
    Next
    INDEX
    Explanations

    consequence and continuation words

    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
    èĩªæĿ¥
    -0.09
    èĻij
    -0.09
    ascript
    -0.09
    åłĩ
    -0.09
    éĢłæĪIJäºĨ
    -0.09
    é¢ĦæĸĻ
    -0.09
    çĭĥ
    -0.09
    èµ°åĩºæĿ¥
    -0.08
    èĻ¹æ¡¥
    -0.08
    åīįçŀ»æĢ§
    -0.08
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.21
    ä»İèĢĮ
    0.14
    éĹ´æİ¥
    0.13
     thereby
    0.09
    继
    0.09
     ultimately
    0.09
    ä¹Łå°±
    0.09
     potentially
    0.09
    TEX
    0.09
    íķı
    0.09
    Activations Density 0.199%

    No Known Activations