© 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. 34003
    Prev
    Next
    INDEX
    Explanations

    telescope makers and facility

    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
    éī´
    -0.09
    éĴī
    -0.09
     pet
    -0.09
    avic
    -0.09
    Sand
    -0.08
    iele
    -0.08
    çıŃ级
    -0.08
    ä¸įçķĻ
    -0.08
    arga
    -0.08
    顶
    -0.08
    POSITIVE LOGITS
    æĤ¼
    0.10
    å¼Ģåı£
    0.09
    INA
    0.08
     mừng
    0.08
    çİ·
    0.08
    å·į
    0.08
    åı£å¾Ħ
    0.08
    为ä¸ŃåĽ½
    0.08
    ä¼Ļ
    0.08
    usto
    0.08
    Activations Density 0.066%

    No Known Activations