© 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. 39414
    Prev
    Next
    INDEX
    Explanations

    I

    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
    ãĢĤãĢĮ
    -0.26
    CHED
    -0.26
    ;]/
    -0.24
    ician
    -0.24
     «
    -0.24
    ROWN
    -0.24
     Adult
    -0.24
    åİĨåı²æĸ°é«ĺ
    -0.24
    aches
    -0.24
    MARY
    -0.24
    POSITIVE LOGITS
    è¡Ķ
    0.27
     pup
    0.27
    æĺİ天
    0.25
     desn
    0.25
    å¥ī
    0.25
    å±ĭ顶
    0.25
     rumor
    0.24
    vis
    0.24
     ↵        ↵
    0.24
     conserv
    0.24
    Activations Density 1.972%

    No Known Activations