© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1039
    Prev
    Next
    INDEX
    Explanations

    judicial circuit or district

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ever
    -0.24
     Rudd
    -0.23
     nu
    -0.23
    elm
    -0.23
     Kush
    -0.22
     bedding
    -0.22
    ish
    -0.22
    STR
    -0.22
    è¿Ļ个è¡Įä¸ļ
    -0.22
    ç§įç§į
    -0.21
    POSITIVE LOGITS
    ouble
    0.27
    longleftrightarrow
    0.23
     organizational
    0.22
    mage
    0.22
    çĿģ
    0.22
    lace
    0.21
    åīĸ
    0.21
    å¿ı
    0.20
     Largest
    0.20
    çIJı
    0.20
    Activations Density 0.004%

    No Known Activations