© 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. 30053
    Prev
    Next
    INDEX
    Explanations

    Ebert, surgery, Stuxnet, iOS, crystal structures

    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
    è¹Ī
    -0.09
    ilight
    -0.09
    riad
    -0.09
    .dep
    -0.09
    éĴı
    -0.09
    жи
    -0.09
    èĻļ空
    -0.09
    _zone
    -0.09
    éĺĥ
    -0.09
    incer
    -0.08
    POSITIVE LOGITS
    ÑĥÑī
    0.10
    shima
    0.09
    ä¼ij
    0.09
    éĿ¢éĥ¨
    0.09
    头éĥ¨
    0.08
    æŀģé«ĺ
    0.08
     surgery
    0.08
    ÑĮев
    0.08
    éĤ£ä»½
    0.08
    伧
    0.08
    Activations Density 0.004%

    No Known Activations