© 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. 40214
    Prev
    Next
    INDEX
    Explanations

    colors

    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
    ︶
    -0.31
    passport
    -0.28
     IC
    -0.26
    ICO
    -0.26
    ingly
    -0.24
    >>↵
    -0.24
    agas
    -0.23
    ndern
    -0.23
    itled
    -0.23
    ->↵
    -0.23
    POSITIVE LOGITS
    ç»ĦåIJĪ
    0.29
    çħ§
    0.26
    using
    0.26
    anges
    0.26
    ansi
    0.25
     Reich
    0.25
    nie
    0.25
     either
    0.25
    ç«ĭ
    0.25
    ayo
    0.25
    Activations Density 0.083%

    No Known Activations