© 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. 41040
    Prev
    Next
    INDEX
    Explanations

    large quantities, amounts, numbers

    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
    ost
    -0.30
    å°ģ
    -0.28
    eren
    -0.28
    OST
    -0.27
     running
    -0.27
     tek
    -0.26
    横
    -0.26
    Ùģا
    -0.25
    ADO
    -0.25
    edBy
    -0.25
    POSITIVE LOGITS
    enschaft
    0.27
    rophe
    0.27
    dice
    0.26
     constitu
    0.26
    \Container
    0.25
    -parts
    0.24
    é¢Ĭ
    0.24
    лев
    0.24
    .Properties
    0.24
    /license
    0.24
    Activations Density 0.133%

    No Known Activations