© 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. 88601
    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
    çļĦçĹĩçĬ¶
    -0.25
    zo
    -0.24
    åľ¨æĪijçļĦ
    -0.24
    Ñģин
    -0.23
    åľ¨åĵª
    -0.23
    åľ°çIJĥä¸Ĭ
    -0.23
    "](
    -0.23
     versus
    -0.23
    صÙĦ
    -0.22
    ellt
    -0.22
    POSITIVE LOGITS
    ä¸Ģçľĭ
    0.25
    æĬĢæľ¯æĶ¯æĮģ
    0.24
    主æĴŃ
    0.23
    ä¹ĺ
    0.23
    åĬĽæ°Ķ
    0.23
     présente
    0.23
     Ji
    0.23
    ä¸įåıĬ
    0.23
    egin
    0.22
    moz
    0.22
    Activations Density 1.464%

    No Known Activations

    This feature has no known activations.