© 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. 48040
    Prev
    Next
    INDEX
    Explanations

    click here

    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
    åķľ
    -0.10
    usi
    -0.10
    combe
    -0.09
    æĻļé¥Ń
    -0.09
    aurus
    -0.09
    央è§Ĩ
    -0.09
    è¾Ī
    -0.09
    åĪ©çĶ¨æĤ¨çļĦ
    -0.09
    åIJµ
    -0.09
    å·¥ä½ľç»Ħ
    -0.09
    POSITIVE LOGITS
    atest
    0.09
     Opening
    0.08
    åĺ»
    0.08
    åıĹçIJĨ
    0.08
     opening
    0.08
    æľ¬è´¨ä¸Ĭ
    0.07
    dling
    0.07
     Marxist
    0.07
    ä¸ĬæĿ¥
    0.07
    .spark
    0.07
    Activations Density 0.033%

    No Known Activations