© 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. 56131
    Prev
    Next
    INDEX
    Explanations

    Northeast US states

    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
    æĭīæĸ¯
    -0.10
    æĪIJéĥ½
    -0.10
    çĸ¯çĭĤ
    -0.10
    ç¬ij声
    -0.09
    ä¹Łå°±æĺ¯è¯´
    -0.09
    说æľį
    -0.09
    常æĢģ
    -0.09
    å¾Ļ
    -0.09
    anches
    -0.09
    æĬĺ
    -0.09
    POSITIVE LOGITS
    常å·ŀ
    0.12
     NJ
    0.11
     Jersey
    0.11
     Worcester
    0.10
    éķ¿ä¸īè§Ĵ
    0.10
    西æ´ĭ
    0.10
     Rutgers
    0.10
     Massachusetts
    0.10
     Connecticut
    0.10
    NJ
    0.10
    Activations Density 0.351%

    No Known Activations