© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    serious complications

    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
    ocker
    -0.09
    åıĸæļĸ
    -0.08
    饯
    -0.08
    æī®
    -0.08
    [to
    -0.08
     Antar
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
    æ´Ĺ澡
    -0.08
    hone
    -0.08
    iz
    -0.08
    POSITIVE LOGITS
     Serious
    0.13
     serious
    0.11
    serious
    0.11
    æĶ¸
    0.11
    严èĤĥ
    0.11
    èѦåijĬ
    0.11
    æŶåĪ»
    0.10
    bens
    0.10
    shaw
    0.10
    insky
    0.09
    Activations Density 0.030%

    No Known Activations