© 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. 37003
    Prev
    Next
    INDEX
    Explanations

    international cities and destinations

    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
    åľ¨å¤ĸéĿ¢
    -0.08
    éĢ¸
    -0.08
    ä¾Ľæ°´
    -0.08
    æµ·æ·Ģ
    -0.08
    ched
    -0.08
    Breaking
    -0.08
    åľ¨å¤ĸ
    -0.08
    æ³±
    -0.08
    èĬ³
    -0.08
     Compact
    -0.08
    POSITIVE LOGITS
    缮çļĦåľ°
    0.12
    Dest
    0.11
    çĽ´è¾¾
    0.10
    ä¸Ģè·¯ä¸Ĭ
    0.10
    ä¸įè¿ľ
    0.10
    dest
    0.10
    destination
    0.10
     destinations
    0.09
    쯤
    0.09
    éĢĶä¸Ń
    0.09
    Activations Density 0.093%

    No Known Activations