© 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. 37774
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
    褫
    -0.11
    åĢĻ
    -0.09
    elight
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.08
    åĴĮæĶ¯æĮģ
    -0.08
    èµŀç¾İ
    -0.08
    åĪ°ä½į
    -0.08
    èĬŃ
    -0.08
    åĽ½åĨħ
    -0.08
    çļĤ
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.12
    ä¹ĥèĩ³
    0.11
    -wide
    0.10
    åīįè¿Ľ
    0.10
    éªĦåĤ²
    0.09
    uese
    0.09
    gor
    0.09
    ians
    0.09
    åīįéĢĶ
    0.09
    çļĦæķ´ä½ĵ
    0.09
    Activations Density 0.055%

    No Known Activations