© 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. 1645
    Prev
    Next
    INDEX
    Explanations

    economy challenges and uncertainty

    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
     simply
    -0.08
    åIJ¦
    -0.08
    yers
    -0.08
    ãģªãģ®ãģ§ãģĻ
    -0.08
     Cann
    -0.08
     пÑĢоÑģÑĤо
    -0.08
    ç¿»
    -0.08
    çŁ¥éģĵäºĨ
    -0.08
    çĸĨ
    -0.08
    çİ©
    -0.07
    POSITIVE LOGITS
    ä½ľæĸĩ
    0.10
    _DIAG
    0.10
    è¾ĥ强çļĦ
    0.10
    è¿ĺæĺ¯ä¼ļ
    0.09
    稳åģ¥
    0.09
    ä¿Ł
    0.09
    æºĺ
    0.09
    è¾ĥ强
    0.09
    ä¹ĭéĻħ
    0.09
    严峻
    0.09
    Activations Density 0.032%

    No Known Activations