© 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. 87803
    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
    ature
    -0.28
    .openqa
    -0.27
    åIJĦç±»
    -0.26
     unauthorized
    -0.24
    åIJįå½ķ
    -0.24
     mannen
    -0.23
    çıŃ级
    -0.23
     Synopsis
    -0.23
     Männer
    -0.23
    æ¡Īä¾ĭ
    -0.23
    POSITIVE LOGITS
    reuse
    0.25
    alfa
    0.25
    aland
    0.25
     compens
    0.25
    sto
    0.25
    èĵĦ
    0.25
     harness
    0.24
    ski
    0.24
     resil
    0.24
     MAG
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.