© 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. 4996
    Prev
    Next
    INDEX
    Explanations

    Texas courts and cities

    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
    æī¿å¾·
    -0.11
     Vermont
    -0.10
    icy
    -0.10
    æłªæ´²
    -0.10
    å½Ŀ
    -0.09
    /std
    -0.09
    å®ľæĺĮ
    -0.09
    icts
    -0.09
    ä¸ĢåıĮ
    -0.09
    红è±Ĩ
    -0.09
    POSITIVE LOGITS
     Texas
    0.21
    Texas
    0.20
     Texans
    0.19
     TEX
    0.17
    å¾·å·ŀ
    0.17
    Houston
    0.17
     Houston
    0.17
     Tex
    0.16
    TEX
    0.16
     texas
    0.16
    Activations Density 0.259%

    No Known Activations