© 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. 112333
    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
    abay
    -0.30
    åŁİå¸Ĥåıijå±ķ
    -0.26
     ray
    -0.26
    åĸ·
    -0.25
    /arm
    -0.25
    æ°¸è¿ľ
    -0.25
    åı¶åŃIJ
    -0.24
    -roll
    -0.24
    ï¼ļ"
    -0.24
     maç
    -0.24
    POSITIVE LOGITS
    epam
    0.26
    OrDefault
    0.26
    /^
    0.25
    绩
    0.24
    çĸ¾
    0.24
    iano
    0.23
    abol
    0.23
    bridge
    0.23
    >H
    0.23
    oters
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.