© 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. 30-TRANSCODER-HP
    7. 95683
    Prev
    Next
    INDEX
    Explanations

    Business-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ĢæĶ¾å¼ı
    -0.29
    .Lang
    -0.28
    çݯå¢ĥä¸Ń
    -0.27
    ãģ¤ãģĭ
    -0.27
     stock
    -0.27
     Lang
    -0.26
    Lang
    -0.26
    еÑĢж
    -0.26
     Ling
    -0.25
    @if
    -0.25
    POSITIVE LOGITS
    expense
    0.28
     negotiating
    0.28
    æ´¾
    0.26
    线
    0.26
     cost
    0.25
    facet
    0.25
    xing
    0.25
    ç»ıæµİåѦ
    0.25
    éĤ»
    0.25
     conven
    0.24
    Activations Density 0.110%

    No Known Activations