© 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. 23731
    Prev
    Next
    INDEX
    Explanations

    success and positive outcomes

    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
    åıĻ
    -0.11
    港澳
    -0.10
    èIJĿåįľ
    -0.09
    è°²
    -0.09
    è¯ĦåĪ¤
    -0.09
    PUR
    -0.09
    çIJ¢ç£¨
    -0.09
    tera
    -0.09
    深度
    -0.08
    å¡«è¡¥
    -0.08
    POSITIVE LOGITS
     productivity
    0.10
     Wich
    0.10
    çĶŁäº§åĬĽ
    0.09
     ÑĩÑĤ
    0.09
    羡
    0.08
    lias
    0.08
     ÑģоÑģÑĤав
    0.08
    æ½ľèĥ½
    0.08
     Cove
    0.08
    æĪIJéķ¿
    0.08
    Activations Density 0.117%

    No Known Activations