© 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. 39145
    Prev
    Next
    INDEX
    Explanations

    suboptimal, weak, mediocre

    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
    åħ¼
    -0.11
    ä¼Łå¤§
    -0.10
    èѦæĥķ
    -0.10
    ä¼ijåģĩ
    -0.10
    翳
    -0.09
    æ´¾
    -0.09
    storybook
    -0.09
    StdString
    -0.09
    dÄĻ
    -0.09
    akens
    -0.09
    POSITIVE LOGITS
    åįģ足
    0.09
    opt
    0.09
    缴æݥ影åĵį
    0.09
     Bang
    0.08
     overall
    0.08
    ens
    0.08
    land
    0.08
    landers
    0.08
    aze
    0.08
    没åķ¥
    0.08
    Activations Density 0.017%

    No Known Activations