© 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. 14-TRANSCODER-HP
    7. 39471
    Prev
    Next
    INDEX
    Explanations

    Compulsions, programs, clinical trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     hypert
    -0.25
    äºĨä¸Ģåı£
    -0.25
    .scheme
    -0.25
    $get
    -0.25
    çīĩ段
    -0.25
     jakie
    -0.25
    .Slice
    -0.24
    andel
    -0.24
    nia
    -0.24
    ãĥĥãĤ·ãĥ¥
    -0.24
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.28
    equ
    0.27
    asa
    0.27
     Cond
    0.26
    rist
    0.25
    -prop
    0.25
    her
    0.25
     Equ
    0.24
    alternate
    0.24
     Emit
    0.24
    Activations Density 0.074%

    No Known Activations