© 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. 1587
    Prev
    Next
    INDEX
    Explanations

    housing

    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
    åľºéĿ¢
    -0.10
    çİĭåŃIJ
    -0.09
    稿
    -0.09
    mary
    -0.09
    ç«¿
    -0.08
    åł
    -0.08
    arella
    -0.08
    è°£è¨Ģ
    -0.08
    èĪ¸
    -0.08
    orda
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.13
    éĩĮçļĦ
    0.10
    mates
    0.09
    agem
    0.09
    æľīä¸Ģ次
    0.09
    .tem
    0.09
    _browser
    0.09
    ä½ij
    0.08
    ä¸įåĬ¨
    0.08
    LastError
    0.08
    Activations Density 0.104%

    No Known Activations