© 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. 8345
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    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
    让大家
    -0.27
    ulu
    -0.26
    å·²ä¹ħçļĦ
    -0.26
    hee
    -0.25
    ä»Ĺ
    -0.24
    elly
    -0.24
     unanimous
    -0.24
    åį±å®³
    -0.24
    obot
    -0.24
    çļĦåį±å®³
    -0.24
    POSITIVE LOGITS
    èĢĥ
    0.26
     Net
    0.26
    elaide
    0.25
    rt
    0.24
     preced
    0.24
     rt
    0.24
    è´´
    0.23
     Leap
    0.23
    /topics
    0.23
    WithURL
    0.23
    Activations Density 0.001%

    No Known Activations