© 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. 41143
    Prev
    Next
    INDEX
    Explanations

    hole

    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
    artment
    -0.34
    illez
    -0.28
    ialog
    -0.28
    èł²
    -0.28
    -mask
    -0.27
    aption
    -0.26
    dia
    -0.25
    éªĭ
    -0.23
    itial
    -0.23
    ctl
    -0.23
    POSITIVE LOGITS
     Spy
    0.27
    impl
    0.26
    +len
    0.25
     spear
    0.25
    å¾Īéķ¿
    0.25
    .fe
    0.25
    eyes
    0.25
    yard
    0.25
    âĨij
    0.24
    horse
    0.24
    Activations Density 6.442%

    No Known Activations