© 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. 8453
    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
    åħļç»Ħ书记
    -0.31
    ilton
    -0.27
    .upper
    -0.26
    ä¸ĢæľŁ
    -0.26
    _EL
    -0.25
     -*-
    -0.25
    ilan
    -0.25
    ç¡®
    -0.25
    ucose
    -0.25
     chấp
    -0.25
    POSITIVE LOGITS
     roma
    0.28
    ceso
    0.26
    reck
    0.25
    æĹ¶è¾°
    0.25
    èµ°ä¸ĭåİ»
    0.25
     rom
    0.25
    âĢ¦”↵↵
    0.24
    æĹĹå¸ľ
    0.24
    ä¸įåħĭ
    0.24
    åĮ¡
    0.24
    Activations Density 0.055%

    No Known Activations

    This feature has no known activations.