© 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. 17428
    Prev
    Next
    INDEX
    Explanations

    California District Court Tax

    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
    å¾IJå·ŀ
    -0.15
    çī¤
    -0.11
    éĤ³
    -0.11
    缴è¾ĸå¸Ĥ
    -0.11
    çĿ¢
    -0.10
    å°ı康
    -0.10
    临æ²Ĥ
    -0.10
    天津å¸Ĥ
    -0.10
    沧å·ŀ
    -0.10
    é½IJé²ģ
    -0.09
    POSITIVE LOGITS
     California
    0.19
    California
    0.19
     Californ
    0.18
    åĬłå·ŀ
    0.18
     Sacramento
    0.17
     california
    0.16
    æĪIJéĥ½
    0.15
     Pasadena
    0.15
     Fresno
    0.15
     Cupertino
    0.14
    Activations Density 0.620%

    No Known Activations