© 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. 12-TRANSCODER-HP
    7. 23510
    Prev
    Next
    INDEX
    Explanations

    stock market and finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ault
    -0.26
    åĿĽ
    -0.25
    -League
    -0.25
    è¦ģä¹Ī
    -0.25
    ombat
    -0.25
     Ingram
    -0.25
    oland
    -0.25
    park
    -0.24
    ç»ĵå®ŀ
    -0.24
    çľĭä¸įåĩº
    -0.24
    POSITIVE LOGITS
    anno
    0.27
    çľ¼ä¸Ń
    0.27
     saw
    0.27
    _caps
    0.26
    鸳
    0.25
    -coded
    0.24
    对åħ¶
    0.24
    å°Ĩåħ¶
    0.24
    åĬ¨æĢģ
    0.24
    ÑģоÑģ
    0.24
    Activations Density 0.001%

    No Known Activations