© 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. 141906
    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
    ä¸Ģ棵
    -0.25
    士
    -0.25
    olith
    -0.25
     mess
    -0.24
     Behind
    -0.24
    MIT
    -0.23
     Nations
    -0.23
    vak
    -0.22
    ãģ»ãģĨ
    -0.22
    ãģij
    -0.22
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.28
    ä¸įåİ»
    0.28
    æįŁ
    0.27
    rowable
    0.25
    çļĦ表æĥħ
    0.25
    urers
    0.25
     rob
    0.25
    inden
    0.24
    æ³ķå¾ĭ顾éĹ®
    0.24
    intColor
    0.24
    Activations Density 5.485%

    No Known Activations

    This feature has no known activations.