© 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. 8182
    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
    ï¼Įé»ĺ认
    -0.28
    輩
    -0.26
    ZW
    -0.26
    è¿Ļ让
    -0.26
     amp
    -0.26
    èĥº
    -0.26
     rẻ
    -0.26
     )č↵č↵
    -0.25
    解读
    -0.25
    èĮ¹
    -0.25
    POSITIVE LOGITS
     care
    0.28
    ĮĢ
    0.28
    å¼ķèµ·
    0.27
    -↵
    0.27
     fundraiser
    0.25
    ltr
    0.25
    éº
    0.24
    WithTitle
    0.24
     cra
    0.24
    æĮĤ
    0.24
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.