© 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. 19-TRANSCODER-HP
    7. 8309
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.30
    »
    -0.28
    ome
    -0.28
    综åIJĪä½ĵ
    -0.28
     many
    -0.27
     slashed
    -0.27
    许å¤ļ
    -0.25
    ç´łè´¨æķĻèĤ²
    -0.24
    ãģ»ãģ¨
    -0.24
    ull
    -0.24
    POSITIVE LOGITS
    èµĸ以
    0.29
    marshall
    0.26
     Sized
    0.26
    lessly
    0.26
    ราย
    0.26
     Tencent
    0.26
     Prel
    0.25
     recipro
    0.25
    强èĢħ
    0.25
    brane
    0.24
    Activations Density 0.098%

    No Known Activations

    This feature has no known activations.