© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    arrival of items

    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
    ãĤ½ãĥ³
    -0.10
    æ¼Ķ
    -0.09
    Surname
    -0.08
    roke
    -0.08
    æľīéĻIJ
    -0.08
    uent
    -0.08
     avi
    -0.08
    empor
    -0.08
     Extraction
    -0.08
    èĪĢ
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.16
     arrives
    0.14
     arrive
    0.14
     arriving
    0.14
     arrived
    0.13
    åĪ°æĿ¥
    0.13
    æĿ¥ä¸´
    0.13
    æĬµè¾¾
    0.13
     arrival
    0.13
    åĪ°è¾¾
    0.12
    Activations Density 0.103%

    No Known Activations