© 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. 8190
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    utar
    -0.25
    fühl
    -0.24
    ĽĦ
    -0.24
    åĽºçĦ¶
    -0.24
    åIJIJ
    -0.24
     compound
    -0.23
    èĪŀ
    -0.23
     guess
    -0.23
    ipples
    -0.23
    rench
    -0.23
    POSITIVE LOGITS
     Explanation
    0.27
    解éĩĬ
    0.26
    对å¾ħ
    0.26
    xit
    0.26
    aroo
    0.25
    ØŃداث
    0.24
     FileMode
    0.24
     filmed
    0.24
     explanation
    0.23
    :nil
    0.23
    Activations Density 0.082%

    No Known Activations