© 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. 58992
    Prev
    Next
    INDEX
    Explanations

    crowdsourcing and volunteers

    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
    èIJ¥ä¸ļ
    -0.11
    orough
    -0.10
    iland
    -0.09
    oha
    -0.09
    éĻIJ
    -0.09
    /function
    -0.08
    çī§åľº
    -0.08
    åŁı
    -0.08
    è¦ģåľ¨
    -0.08
    åĮł
    -0.08
    POSITIVE LOGITS
     citizen
    0.13
    åħ¬æ°ij
    0.12
     Citizen
    0.12
    æįIJçĮ®
    0.10
    å¿ĹæĦ¿èĢħ
    0.10
    å¹´æĬ¥
    0.10
     доб
    0.10
    精度
    0.09
    ä¸ĬæĬ¥
    0.09
     volunteers
    0.09
    Activations Density 0.055%

    No Known Activations