© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149246
    Prev
    Next
    INDEX
    Explanations

    Food and dishes

    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
    Negative Logits
     Gamb
    -0.25
    身亡
    -0.25
    nge
    -0.24
    cling
    -0.24
    umat
    -0.24
    ãĥªãĥķãĤ©
    -0.23
     Boo
    -0.23
     Bart
    -0.23
     Lamar
    -0.23
    éĩĬ
    -0.22
    POSITIVE LOGITS
    trak
    0.28
    icular
    0.26
    ä¸ĢåıĮ
    0.26
    itecture
    0.24
    èĢĮåİ»
    0.24
    åİ»åĮ»éĻ¢
    0.24
    è¿Ļ件
    0.23
    lights
    0.23
     endorsed
    0.23
    ĥĿ
    0.23
    Activations Density 0.759%

    No Known Activations