© 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. 22-TRANSCODER-HP
    7. 98786
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±Ĭ
    -0.31
    dest
    -0.29
     flu
    -0.27
    uctions
    -0.26
    -origin
    -0.25
    迹
    -0.25
    pal
    -0.25
     sag
    -0.25
     capital
    -0.24
     palm
    -0.24
    POSITIVE LOGITS
     beds
    0.26
    OCK
    0.24
    âĺĿ
    0.24
    audi
    0.24
     sẵn
    0.24
    ready
    0.24
    [js
    0.23
    )][
    0.23
    æ²īé»ĺ
    0.23
    (js
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.