© 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. 23569
    Prev
    Next
    INDEX
    Explanations

    business/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
    lazy
    -0.32
     ourselves
    -0.30
    åĴª
    -0.29
     sealing
    -0.28
    .setInput
    -0.28
     cursed
    -0.25
     enclosed
    -0.24
     lazy
    -0.24
     humanity
    -0.24
     mid
    -0.23
    POSITIVE LOGITS
    alls
    0.28
     ceramics
    0.26
    extensions
    0.25
    zos
    0.25
    à¹ĥหà¸į
    0.24
    åĢ¾
    0.24
    _OVERFLOW
    0.24
    hog
    0.24
    èijĹ
    0.24
    arding
    0.24
    Activations Density 0.001%

    No Known Activations