© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21335
    Prev
    Next
    INDEX
    Explanations

    despite adversity or when conditions change

    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
    让èĩªå·±
    -0.09
    æĮŀ
    -0.09
    unami
    -0.09
    羡
    -0.09
    饥饿
    -0.09
    veau
    -0.09
    embr
    -0.08
    наÑĩ
    -0.08
    æĪ¿ä¸ľ
    -0.08
    é»ĺå¥ij
    -0.08
    POSITIVE LOGITS
     challenging
    0.10
     tricky
    0.09
    _challenge
    0.09
    èī°
    0.09
    åĬ¿
    0.08
    jab
    0.08
    å¾Īéĩįè¦ģ
    0.08
    éĽ£ãģĹãģĦ
    0.08
    è¾Ľèĭ¦
    0.08
     challenge
    0.08
    Activations Density 0.180%

    No Known Activations