© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20797
    Prev
    Next
    INDEX
    Explanations

    vicinity, neighborhood, area

    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
    âķij
    -0.10
    为客æĪ·
    -0.10
    åĽ½ç±į
    -0.09
    idot
    -0.09
    è·Łä¸įä¸Ĭ
    -0.09
    otto
    -0.09
    åIJİéĿ¢çļĦ
    -0.09
    å¹ķ
    -0.09
    褥
    -0.09
    ç²ķ
    -0.09
    POSITIVE LOGITS
     vicinity
    0.19
    éĻĦè¿ij
    0.16
    åij¨åĽ´
    0.16
     area
    0.14
    åij¨åĽ´çļĦ
    0.13
     around
    0.13
    èĮĥåĽ´åĨħ
    0.13
     neighborhood
    0.13
    åĽ´ç»ķ
    0.13
    ä¸Ģ带
    0.12
    Activations Density 0.116%

    No Known Activations