© 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. 64039
    Prev
    Next
    INDEX
    Explanations

    over the

    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
    izr
    -0.11
    çŃĿ
    -0.10
    æŃĮ
    -0.09
    åľ¨åĮĹ京
    -0.09
    è´¡
    -0.09
    çİ©
    -0.09
    åĪģ
    -0.09
    hurst
    -0.09
     Storm
    -0.09
     Plan
    -0.09
    POSITIVE LOGITS
    åºŁæŧ
    0.10
    æŁ¥éĺħ
    0.09
    éĻ¢
    0.09
    é¤Ĭ
    0.09
    PELL
    0.09
    iler
    0.08
    èĩ³ä¸Ĭ
    0.08
    åħ»
    0.08
    åºŁå¼ĥ
    0.08
    æīĶ
    0.08
    Activations Density 0.043%

    No Known Activations