© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41025
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ceptors
    -0.26
     tracer
    -0.25
    ased
    -0.24
    .Try
    -0.24
    åı¯æĢľ
    -0.24
    emens
    -0.24
    çľĭæĿ¥
    -0.23
    ingers
    -0.23
    mts
    -0.23
    åIJ¬å®Į
    -0.23
    POSITIVE LOGITS
     Ren
    0.27
     Rim
    0.26
     ['
    0.26
    åĩ¿
    0.25
    糧
    0.25
    atories
    0.24
    (expect
    0.24
     Freed
    0.24
    å¤ķ
    0.24
     Rem
    0.23
    Activations Density 0.061%

    No Known Activations