© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 234
    Prev
    Next
    INDEX
    Explanations

    landmasses and geographical locations

    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
    mith
    -0.24
    REM
    -0.23
    大纲
    -0.22
    èĥ¶åĽĬ
    -0.22
    ä¸Ģ款
    -0.22
    midt
    -0.21
    plets
    -0.21
    éħIJ
    -0.21
    åħ¨å®¶
    -0.21
    amen
    -0.21
    POSITIVE LOGITS
    acre
    0.24
    åŁł
    0.22
    åĦ¿
    0.21
    åľ°åĮº
    0.21
    åİ¢
    0.21
    haven
    0.21
    zion
    0.20
    wis
    0.20
    locking
    0.20
    xon
    0.20
    Activations Density 0.003%

    No Known Activations