© 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. 18-TRANSCODER-HP
    7. 89907
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦéĢļçŁ¥
    -0.24
    çµĤãĤıãĤĬ
    -0.23
     cÆ°á»Ŀng
    -0.23
    åĮĸè¿Ľç¨ĭ
    -0.23
     Nord
    -0.23
    ause
    -0.22
    æ°ĽåĽ´
    -0.22
    /host
    -0.22
     stair
    -0.22
    aign
    -0.22
    POSITIVE LOGITS
    ...]↵↵
    0.26
    âĸ¾
    0.26
    fieldname
    0.25
    ystack
    0.25
    opath
    0.25
    çľĭ好
    0.24
    ugen
    0.24
    è²Į
    0.24
    åı¯è§ģ
    0.24
    åIJĦè¡Į
    0.23
    Activations Density 3.881%

    No Known Activations

    This feature has no known activations.