© 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. 7674
    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
    åĽºå®ļ
    -0.27
    -long
    -0.26
    èijĹ
    -0.26
     ÑĩиÑģл
    -0.24
     hitch
    -0.24
    imus
    -0.24
     specifying
    -0.24
    oning
    -0.24
    ibo
    -0.24
    åı¯ä»¥çĽ´æİ¥
    -0.23
    POSITIVE LOGITS
    åħħ滿
    0.24
    .SDK
    0.24
     McMahon
    0.24
    åİ»çľĭçľĭ
    0.24
    imity
    0.23
    SAT
    0.23
    çij¶
    0.22
     Hall
    0.22
    xBD
    0.22
    姿
    0.22
    Activations Density 0.823%

    No Known Activations

    This feature has no known activations.