© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17762
    Prev
    Next
    INDEX
    Explanations

    city becoming itself

    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
    elsing
    -0.11
    æĿ¥èĩªäºİ
    -0.10
    Crow
    -0.09
    è¿ĽéŨ
    -0.09
    å½ĵäºĭ人
    -0.09
    åºĹåĨħ
    -0.09
    è¿Ļæī¹
    -0.08
    åĽ½å®¶éĺŁ
    -0.08
    é¾Ľ
    -0.08
    å¼ĵ
    -0.08
    POSITIVE LOGITS
     city
    0.18
    è¿Ļ座åŁİå¸Ĥ
    0.17
    -city
    0.17
    å¸Ĥä¸Ńå¿ĥ
    0.16
    å¸Ĥãģ®
    0.15
    (city
    0.15
    å¸Ĥ
    0.14
    åŁİå¸ĤçļĦ
    0.14
    åŁİ
    0.14
    city
    0.14
    Activations Density 0.276%

    No Known Activations