© 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. 27403
    Prev
    Next
    INDEX
    Explanations

    future actions or decisions

    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
    rlen
    -0.10
    dings
    -0.10
    笼
    -0.09
    çıŀ
    -0.09
    缮çļĦ
    -0.09
    èµ°å»Ĭ
    -0.09
    åŁºæľ¬ä¸Ĭéĥ½
    -0.09
    ITIONS
    -0.09
    åĨµ
    -0.09
    ç»ıå¼Ģ
    -0.09
    POSITIVE LOGITS
    ä¸įæĥľ
    0.10
    æĤ²åī§
    0.09
    åıī
    0.09
    è¡ĮåĬ¨
    0.09
    追æ±Ĥ
    0.08
    çļĪ
    0.08
    æī§æĦı
    0.08
    ä¸įåĪ©äºİ
    0.08
    VER
    0.08
     action
    0.08
    Activations Density 0.039%

    No Known Activations