© 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. 40147
    Prev
    Next
    INDEX
    Explanations

    thought, uncertainty

    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
     egt
    -0.25
     NAFTA
    -0.25
    oble
    -0.24
    -play
    -0.24
    doll
    -0.24
     framing
    -0.24
    è²ī
    -0.23
     frameworks
    -0.23
    ég
    -0.23
     Heg
    -0.23
    POSITIVE LOGITS
    ivel
    0.30
     vacuum
    0.28
    èĩ¾
    0.27
    绣çŃ¹æİ¨è¿Ľ
    0.26
    ä¸įæĩĪ
    0.26
     carn
    0.25
    arel
    0.25
     vest
    0.25
    isSelected
    0.25
    åıĪ
    0.25
    Activations Density 0.103%

    No Known Activations