© 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. 63472
    Prev
    Next
    INDEX
    Explanations

    seattle region geography

    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
    常å·ŀ
    -0.10
    ạn
    -0.10
    åħĥå®Ŀ
    -0.09
    วย
    -0.09
    OfClass
    -0.09
    庵
    -0.09
    çĶ¬
    -0.09
    ãĥ¼ãĤº
    -0.09
    CTION
    -0.09
    太æ¹ĸ
    -0.09
    POSITIVE LOGITS
     Seattle
    0.20
    æĪIJéĥ½
    0.19
    æĪIJéĥ½å¸Ĥ
    0.18
    Seattle
    0.17
    绵éĺ³
    0.16
    åĽĽå·Ŀ
    0.15
    éĥ«
    0.15
    éĤĽ
    0.15
    å¤©åºľ
    0.14
    å·Ŀ
    0.14
    Activations Density 0.132%

    No Known Activations