© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    edge, coax, slipped

    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
    è´Ŀå°Ķ
    -0.08
     Lei
    -0.08
    /documentation
    -0.08
    late
    -0.08
    管
    -0.07
     Mitchell
    -0.07
    docs
    -0.07
    夯
    -0.07
     searchable
    -0.07
    åģ¥
    -0.07
    POSITIVE LOGITS
    æĹĥ
    0.11
    ìĤ´
    0.10
    æľīæīĢ
    0.10
    åĪ©çĽĬ
    0.10
    æ§İ
    0.10
    æ¶Ł
    0.10
    çķ¥æľī
    0.09
    å°ıå°ı
    0.09
    iously
    0.09
    å°ıå°ıçļĦ
    0.09
    Activations Density 0.004%

    No Known Activations