© 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. 7887
    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
     closure
    -0.29
    _wf
    -0.29
     Closure
    -0.29
    rim
    -0.28
    Closure
    -0.26
     vois
    -0.26
     -----↵
    -0.26
    Sing
    -0.25
    åıĪæĺ¯
    -0.25
    /dir
    -0.24
    POSITIVE LOGITS
    éĢļè¡Įè¯ģ
    0.27
    ä¸įå¾Ĺä¸į说
    0.27
     hell
    0.27
    ä¹ĭ乡
    0.27
    blink
    0.26
    slashes
    0.26
     unve
    0.25
    çĪ±æĬ¤
    0.25
     Bols
    0.25
    fre
    0.25
    Activations Density 0.085%

    No Known Activations

    This feature has no known activations.