© 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. 97921
    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
    ificial
    -0.25
     Pri
    -0.24
     Ham
    -0.24
     drawer
    -0.23
    è¦ģ
    -0.23
    illing
    -0.23
    гÑĥ
    -0.23
    iang
    -0.22
    åĩº
    -0.22
    çłģ
    -0.22
    POSITIVE LOGITS
    åŁºå»º
    0.28
    bum
    0.28
    çĮ¿
    0.26
    aders
    0.25
    (iter
    0.25
    devices
    0.25
    ç¥ŀå¥ĩ
    0.25
    è¿Ļæł·ä¸ĢæĿ¥
    0.25
    åĽ½åº¦
    0.25
    åĸľæĤ¦
    0.24
    Activations Density 0.083%

    No Known Activations

    This feature has no known activations.