© 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. 107921
    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
    getto
    -0.34
    åħīèį£
    -0.30
    çĨŁ
    -0.28
    迹
    -0.27
    ard
    -0.27
     wagon
    -0.25
    ix
    -0.25
    oS
    -0.25
    ucht
    -0.25
    unden
    -0.24
    POSITIVE LOGITS
    âĩ¨
    0.25
    اش
    0.24
    (exports
    0.24
    (Post
    0.23
    åºĶæľīçļĦ
    0.23
     Petty
    0.23
    è§Ħå®ļçļĦ
    0.23
     prere
    0.23
    è¯Ŀ说
    0.23
    ibility
    0.22
    Activations Density 1.453%

    No Known Activations

    This feature has no known activations.