© 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. 31642
    Prev
    Next
    INDEX
    Explanations

    county and avenue

    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
     Colonial
    -0.08
    åºĶæĶ¶
    -0.08
    èħ»
    -0.08
    æ¸İ
    -0.08
    ast
    -0.08
    isl
    -0.08
    лÑİд
    -0.08
    isch
    -0.08
    ç§ģ
    -0.08
     ÑģиÑĤ
    -0.08
    POSITIVE LOGITS
    åİ¿
    0.23
     County
    0.19
     county
    0.18
    çľĮ
    0.18
    縣
    0.17
     COUNTY
    0.16
    åİ¿åħ¬å®īå±Ģ
    0.16
    åİ¿æĶ¿åºľ
    0.15
    åİ¿éķ¿
    0.15
    county
    0.14
    Activations Density 0.132%

    No Known Activations