© 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. 111699
    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
    è¿ľå¤Ħ
    -0.28
    sticks
    -0.27
    hiba
    -0.26
     TextAlign
    -0.26
    Specifications
    -0.25
    羣åģĩ
    -0.25
    åĽŀ头çľĭ
    -0.24
    ÅĤow
    -0.24
    ÅĤa
    -0.24
    enis
    -0.24
    POSITIVE LOGITS
    zer
    0.28
    azer
    0.24
    .sources
    0.24
     Bran
    0.24
    å¾ģ
    0.24
    å¾µ
    0.24
    éĻįèIJ½
    0.23
    CESS
    0.23
    åĴĮ社ä¼ļ
    0.23
    _sources
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.