© 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. 97662
    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
    ç½ij讯
    -0.30
     MAL
    -0.27
    ritional
    -0.25
    åĶ¾
    -0.25
    arkan
    -0.23
    itored
    -0.23
    å·¥ç¨ĭè´¨éĩı
    -0.23
    èħĻ
    -0.23
    ductory
    -0.23
    ä¸ĢåĪ»
    -0.23
    POSITIVE LOGITS
    ikit
    0.29
    metics
    0.26
    Lib
    0.26
    ish
    0.25
    \Lib
    0.24
    缸
    0.23
    ubo
    0.23
     firearms
    0.23
    classname
    0.23
    èĬĿ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.