© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63319
    Prev
    Next
    INDEX
    Explanations

    Road to Tokyo

    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
    é«ĺé¢ij
    -0.09
    éĺµ
    -0.09
    ä¸į代表
    -0.09
    è¿Ļä¹Īåģļ
    -0.09
    åĽ½å¤ĸ
    -0.09
    anden
    -0.09
    åħ´
    -0.09
    è¿Ŀ
    -0.09
    .Dispatcher
    -0.09
    .ph
    -0.08
    POSITIVE LOGITS
    äºļè¿IJä¼ļ
    0.09
    èĵĿåĽ¾
    0.08
    ptype
    0.08
    åĪ°æĿ¥
    0.08
     Levine
    0.08
    ffff
    0.08
    åįģä¸ĩ
    0.08
    Spatial
    0.08
    å¦ĤæľŁ
    0.08
    åIJ¯ç¤º
    0.08
    Activations Density 0.127%

    No Known Activations