© 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. 51210
    Prev
    Next
    INDEX
    Explanations

    visiting a place or person

    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
    夯å®ŀ
    -0.09
    åĿļå®Ī
    -0.09
    erot
    -0.09
    åĨħçļĦ
    -0.08
    ijľ
    -0.08
    éģı
    -0.08
     outgoing
    -0.08
    èĭ¦èĭ¦
    -0.08
    Spy
    -0.08
    åIJijçĿĢ
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.24
    åĪ°æĿ¥
    0.19
    æĿ¥è®¿
    0.18
    è¿Ľé©»
    0.17
    访éĹ®
    0.14
     visiting
    0.14
    åħ¥é©»
    0.14
    æĿ¥ä¸´
    0.14
    èİħ
    0.14
    æĿ¥åĪ°
    0.13
    Activations Density 0.231%

    No Known Activations