© 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. 47993
    Prev
    Next
    INDEX
    Explanations

    memorable unforgettable travel

    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
    çħ
    -0.09
    åħ¬çĶ¨
    -0.09
     togg
    -0.08
     void
    -0.08
    å¸Ķ
    -0.08
    鬼
    -0.08
    èĻļ
    -0.08
    unsupported
    -0.08
    éĻª
    -0.08
    herit
    -0.08
    POSITIVE LOGITS
    éļ¾å¿ĺ
    0.27
    è®°å¿Ĩ
    0.21
     memorable
    0.21
    çļĦè®°å¿Ĩ
    0.17
     unforgettable
    0.17
    è¦ļãģĪ
    0.15
    è®°å¿ĨåĬĽ
    0.15
    è®°å¾Ĺ
    0.15
     memories
    0.15
    åį°è±¡æ·±åĪ»
    0.15
    Activations Density 0.055%

    No Known Activations