© 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. 98741
    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
     bree
    -0.29
    ÑħоÑĤ
    -0.27
     pew
    -0.27
    VID
    -0.24
    вид
    -0.24
    IPP
    -0.24
     irres
    -0.24
    cae
    -0.23
    iful
    -0.23
    vid
    -0.23
    POSITIVE LOGITS
    antino
    0.26
    åĽ½ç«ĭ
    0.26
     sacked
    0.24
    çļĵ
    0.24
    PLAIN
    0.24
    åĭĸ
    0.24
    èµ°ä¸ĭåİ»
    0.24
    errat
    0.24
    anson
    0.24
    <option
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.