© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7517
    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
    è¿ĻéĩĮæĺ¯
    -0.28
    人åĵ¡
    -0.24
     Entered
    -0.24
    ä¸Ģå°ģä¿¡
    -0.24
     immunity
    -0.24
    .charCodeAt
    -0.23
    -INF
    -0.23
     DIR
    -0.23
    èĦĵ
    -0.23
     caracter
    -0.23
    POSITIVE LOGITS
    ulus
    0.28
    å°±å¿ħé¡»
    0.24
    ioxide
    0.24
    便
    0.24
    igsaw
    0.23
    iac
    0.23
    ective
    0.23
    éĵħ
    0.23
    é¥
    0.23
    angkan
    0.23
    Activations Density 1.807%

    No Known Activations

    This feature has no known activations.