© 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. 48904
    Prev
    Next
    INDEX
    Explanations

    financial loss or lost jobs

    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
    aten
    -0.11
    æ¸ħæĻ¨
    -0.08
    èĪ¬
    -0.08
    anten
    -0.08
    å¢Ļå£ģ
    -0.08
     завод
    -0.08
    èĤ¯
    -0.08
    aca
    -0.08
    èĽĩ
    -0.08
    è´¥
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.09
    AMPL
    0.09
    мÑı
    0.09
     ÙħÙĪا
    0.09
    é«»
    0.08
    itics
    0.08
    å¼ĢéŨ
    0.08
    çıij
    0.08
    è¡¢
    0.08
    ahead
    0.08
    Activations Density 0.004%

    No Known Activations