© 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. 20-TRANSCODER-HP
    7. 107085
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıį
    -0.28
    trained
    -0.25
    åĿį
    -0.25
    飧
    -0.24
    isure
    -0.24
    å¦Ĥå®ŀ
    -0.24
     artificially
    -0.24
    åı¸
    -0.24
    åĨ¬å¥¥
    -0.24
    ноÑģÑĤей
    -0.24
    POSITIVE LOGITS
    éĴŀ
    0.29
    еÑĢа
    0.26
    ilies
    0.25
     näm
    0.25
    Award
    0.25
     exec
    0.24
    cedes
    0.24
     Accept
    0.24
    (cos
    0.24
    lashes
    0.24
    Activations Density 12.380%

    No Known Activations

    This feature has no known activations.