© 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. 63084
    Prev
    Next
    INDEX
    Explanations

    evaluating effects and results

    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
    é²ľèĬ±
    -0.09
    大人
    -0.07
    çĤĴèĤ¡
    -0.07
    ÑĤеÑĢ
    -0.07
    为æĪij们
    -0.07
     Active
    -0.07
    hive
    -0.07
    .Style
    -0.07
     mur
    -0.07
    åİŁå§ĭ
    -0.07
    POSITIVE LOGITS
    çĶŁéķ¿
    0.10
    åĨľä¸ļåĨľæĿij
    0.10
    åįĹæĸ¹
    0.10
    æĪijçľģ
    0.10
    饲
    0.10
    åŀĴ
    0.10
    èĮ¬
    0.09
    åķĨä¸ļåĮĸ
    0.09
     ÑħозÑıй
    0.09
    对çŃĸ
    0.09
    Activations Density 0.370%

    No Known Activations