© 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. 53116
    Prev
    Next
    INDEX
    Explanations

    survive the

    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
    ä¾¿å®ľ
    -0.10
    åģľæ»ŀ
    -0.09
    (ERR
    -0.09
    ZN
    -0.08
    èIJ¥åĪ©
    -0.08
    泪
    -0.08
    å¾ĹçĽĬ
    -0.08
    çĽĪåĪ©
    -0.08
    zn
    -0.08
    á»ģm
    -0.08
    POSITIVE LOGITS
    æ´Ĺ礼
    0.11
     scrutiny
    0.11
    èĢĥéªĮ
    0.10
    èĢĮåĩº
    0.10
    诱æĥij
    0.09
    ç½ijç«Ļé¦ĸ页
    0.09
    _LS
    0.09
    顽强
    0.09
    æ¿ĢçĥĪ
    0.09
    åĽ´
    0.09
    Activations Density 0.039%

    No Known Activations