© 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. 130314
    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
    antino
    -0.31
    DIFF
    -0.24
    bedPane
    -0.24
    æݨå¼Ģ
    -0.24
    å°±è¿Ļä¹Ī
    -0.23
    emento
    -0.23
    ä»ħ次äºİ
    -0.23
    athan
    -0.22
    emode
    -0.22
    iteDatabase
    -0.22
    POSITIVE LOGITS
    jas
    0.29
    èµı
    0.25
    Ao
    0.25
    pletely
    0.24
    ROS
    0.24
    æ°´åĪĨ
    0.23
    éĩĩ
    0.22
    .redirect
    0.22
    èĸª
    0.22
    pii
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.