© 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. 19-TRANSCODER-HP
    7. 9665
    Prev
    Next
    INDEX
    Explanations

    dates/years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¹İ
    -0.29
    counter
    -0.27
    cancel
    -0.26
    失败
    -0.25
    失èIJ½
    -0.25
     fails
    -0.25
     ProgressDialog
    -0.24
    æķ°çĻ¾
    -0.24
    steen
    -0.24
    èĢĮ导èĩ´
    -0.24
    POSITIVE LOGITS
     **↵
    0.28
    ignon
    0.25
    irus
    0.24
    rens
    0.24
    uly
    0.24
    inson
    0.24
    Ñģен
    0.24
    åĭĻ
    0.24
    aceous
    0.24
    Bootstrap
    0.24
    Activations Density 0.007%

    No Known Activations