© 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. 88087
    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
    appa
    -0.28
    pta
    -0.25
    .getFont
    -0.24
    æ°ĶåĢĻ
    -0.24
    aland
    -0.24
    .font
    -0.23
    çij¾
    -0.23
     angels
    -0.23
     report
    -0.23
     Without
    -0.23
    POSITIVE LOGITS
    creens
    0.27
    ÄŃ
    0.25
    çĮĩ
    0.23
    è¿Ļä¹Īå¤ļå¹´
    0.23
    è¿«
    0.22
    OUS
    0.22
    æ¦Ķ
    0.22
    ä¸Ģä¸ĭ
    0.22
    /navigation
    0.22
    ä¸İæĹ¶ä¿±
    0.22
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.