© 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. 40819
    Prev
    Next
    INDEX
    Explanations

    File paths

    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
    vection
    -0.31
    cean
    -0.28
    ursal
    -0.28
    >ID
    -0.28
    arts
    -0.27
     ceremonies
    -0.26
     poil
    -0.26
    ByVersion
    -0.26
    ElementsBy
    -0.26
     ceremony
    -0.25
    POSITIVE LOGITS
    ä¸ĢæĿ¡
    0.27
    ander
    0.26
     scal
    0.26
    Statics
    0.26
    U
    0.25
    stantiate
    0.25
    UNDER
    0.25
    个å°ıæŶ
    0.24
    天ä¸ĭ
    0.24
    har
    0.24
    Activations Density 4.351%

    No Known Activations