© 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. 112232
    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
     "[%
    -0.28
    esis
    -0.26
    ulp
    -0.26
    ught
    -0.26
    _endian
    -0.24
     décid
    -0.24
    Sock
    -0.24
     maxSize
    -0.24
    oden
    -0.24
    tery
    -0.24
    POSITIVE LOGITS
    ,
    0.30
     after
    0.30
    after
    0.30
    –
    0.29
     (
    0.29
    -
    0.29
    =
    0.28
     –
    0.27
    5
    0.27
    åĸ
    0.27
    Activations Density 0.822%

    No Known Activations

    This feature has no known activations.