© 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. 40443
    Prev
    Next
    INDEX
    Explanations

    Web-related content

    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
    éĢł
    -0.29
    ients
    -0.28
    CEPT
    -0.27
    ·»
    -0.27
    åĬ²
    -0.26
    -original
    -0.26
    .Master
    -0.26
    ç¦Ģ
    -0.25
     SOFTWARE
    -0.25
    åĬŀ
    -0.25
    POSITIVE LOGITS
    èIJ±
    0.26
    Route
    0.26
    åıijå±ķ模å¼ı
    0.25
    èIJ¥åĪ©
    0.25
    itzer
    0.25
    æĸĩ书
    0.25
    è¡Įä¸ļåıijå±ķ
    0.24
     routed
    0.24
     Route
    0.24
    (Enum
    0.24
    Activations Density 0.968%

    No Known Activations