© 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. 20-TRANSCODER-HP
    7. 64259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢģ人家
    -0.27
     bình
    -0.27
    hor
    -0.26
     Beat
    -0.26
    placement
    -0.26
    Hor
    -0.26
     Horizon
    -0.24
    ulp
    -0.24
    rending
    -0.24
    binding
    -0.24
    POSITIVE LOGITS
    ä¾Ŀ
    0.28
     whites
    0.26
     ogl
    0.26
    gaard
    0.25
    avax
    0.25
    å±Ĥåĩº
    0.24
    ,{"
    0.24
    éĺĶ
    0.24
    ields
    0.24
    anmar
    0.24
    Activations Density 0.467%

    No Known Activations

    This feature has no known activations.