© 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. 63914
    Prev
    Next
    INDEX
    Explanations

    synthetic

    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
    åĬ«
    -0.10
    ãĥ³ãĤ°
    -0.10
    æ·±
    -0.09
    vale
    -0.09
    deen
    -0.09
    nings
    -0.09
    :NS
    -0.09
     Townsend
    -0.08
    .beta
    -0.08
     vá»±c
    -0.08
    POSITIVE LOGITS
    ä¸ŃåĽ½äººæ°ij
    0.10
    ä¸įæĿ¥
    0.09
    ITY
    0.09
    any
    0.09
    åħļåĴĮ
    0.08
    acia
    0.08
    å¼łè´´
    0.08
    ishi
    0.08
    对çħ§æ£ĢæŁ¥
    0.08
    ãĤ«ãĥª
    0.08
    Activations Density 0.028%

    No Known Activations