© 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. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150099
    Prev
    Next
    INDEX
    Explanations

    European Union

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favourable
    -0.29
    YG
    -0.27
     armour
    -0.27
    çļĦæĶ¯æĮģ
    -0.27
    åľ¨ä¸Ģ
    -0.27
     traveller
    -0.26
     Koreans
    -0.26
     modelling
    -0.25
    æĥħåĨµä¸ĭ
    -0.25
     seaw
    -0.24
    POSITIVE LOGITS
    ãĥĩãĤ£ãĥ³ãĤ°
    0.31
     Eur
    0.28
     union
    0.27
     Walt
    0.27
     Subjects
    0.27
     membership
    0.26
     eu
    0.26
    亿åIJ¨
    0.26
    lund
    0.26
     subjects
    0.25
    Activations Density 0.885%

    No Known Activations