© 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. 98148
    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
    umatic
    -0.28
    主è¦ģåĨħ容
    -0.26
    书记
    -0.25
    аÑĤÑĥÑĢ
    -0.24
    leneck
    -0.24
    oftware
    -0.24
     Bram
    -0.24
    å§Ķä¼ļ
    -0.23
     softly
    -0.23
     crisp
    -0.23
    POSITIVE LOGITS
    .serialization
    0.26
    owler
    0.26
     phase
    0.25
    emade
    0.25
    Runner
    0.25
    phase
    0.23
    idor
    0.23
    anzi
    0.23
    cem
    0.23
    åݨ
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.