© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3077
    Prev
    Next
    INDEX
    Explanations

    island or islands

    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
    èIJĥ
    -0.10
    没æľīå¿ħè¦ģ
    -0.09
    stry
    -0.09
     Baghdad
    -0.08
     Ukr
    -0.08
    è¿Ļ段
    -0.08
    åħ¨åĽ½äººå¤§
    -0.08
    positories
    -0.08
    slots
    -0.08
    Slots
    -0.08
    POSITIVE LOGITS
    å²Ľä¸Ĭ
    0.19
    å²Ľ
    0.18
     island
    0.16
    島
    0.16
    å²Ľå±¿
    0.15
     islands
    0.14
     Island
    0.14
    æµ·å²Ľ
    0.12
     Islanders
    0.12
    屿
    0.10
    Activations Density 0.140%

    No Known Activations