© 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. 40058
    Prev
    Next
    INDEX
    Explanations

    one

    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
    大äºĭ
    -0.28
     medida
    -0.27
    "${
    -0.26
    offs
    -0.26
    ãģ»ãģĨ
    -0.26
    rame
    -0.26
    åıĺ
    -0.26
    ventions
    -0.25
    __,↵
    -0.25
    leg
    -0.24
    POSITIVE LOGITS
    Asked
    0.30
     tert
    0.27
    roupe
    0.25
    âĨ©
    0.24
    åĽ°éļ¾
    0.24
     Wednesday
    0.24
     interpolated
    0.23
    ä¸įå°ijäºİ
    0.23
    edBy
    0.23
    çĻ»åħ¥
    0.23
    Activations Density 0.015%

    No Known Activations