© 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. 27-TRANSCODER-HP
    7. 57671
    Prev
    Next
    INDEX
    Explanations

    salary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    被åĬ¨
    -0.33
    zej
    -0.28
    pass
    -0.27
     adopt
    -0.26
    mort
    -0.25
    end
    -0.25
    ıklı
    -0.25
     sole
    -0.25
    _traffic
    -0.25
    uz
    -0.24
    POSITIVE LOGITS
    etched
    0.24
    æĸĩ书
    0.23
     Bench
    0.23
    dez
    0.23
    rupted
    0.23
     benchmarks
    0.23
    rances
    0.23
    æ´Ĺæīĭ
    0.23
    .utilities
    0.22
    åħ·æľīä¸Ģå®ļ
    0.22
    Activations Density 0.076%

    No Known Activations