© 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. 12-TRANSCODER-HP
    7. 22309
    Prev
    Next
    INDEX
    Explanations

    "to be" verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &m
    -0.31
    åī©ä¸ĭ
    -0.26
    åī©ä¸ĭçļĦ
    -0.26
    rozen
    -0.26
    .realpath
    -0.25
    avra
    -0.25
    &e
    -0.24
    &a
    -0.23
    &o
    -0.23
     ValidationError
    -0.23
    POSITIVE LOGITS
     Lis
    0.29
     precisely
    0.27
     char
    0.27
     myster
    0.26
    rotein
    0.26
     gag
    0.26
    æģ°å¥½
    0.25
     scales
    0.25
    -ever
    0.24
    кол
    0.24
    Activations Density 0.006%

    No Known Activations