© 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. 130573
    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
    æĿª
    -0.28
    æłī
    -0.28
    ooter
    -0.27
    etus
    -0.27
    esian
    -0.26
    åħħå®ŀ
    -0.24
    elper
    -0.24
    ble
    -0.24
    ousse
    -0.23
    egral
    -0.23
    POSITIVE LOGITS
    å§ij
    0.30
    _UC
    0.29
    _COD
    0.28
     Ol
    0.24
    Cond
    0.24
    contr
    0.24
     Concord
    0.24
    гÑĢ
    0.23
     compiled
    0.23
    ä¸Ńåľº
    0.23
    Activations Density 19.819%

    No Known Activations

    This feature has no known activations.