© 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. 18-TRANSCODER-HP
    7. 89545
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ither
    -0.28
    orte
    -0.27
    è®©æĽ´å¤ļ
    -0.26
    CMS
    -0.25
    atory
    -0.24
    ä¿ĿéĻ©åħ¬åı¸
    -0.24
    ä¿¡æģ¯æľįåĬ¡
    -0.24
    æĿĢèıĮ
    -0.24
    erre
    -0.24
    æĺ¼å¤ľ
    -0.24
    POSITIVE LOGITS
    stin
    0.32
    licant
    0.28
     Rub
    0.25
    .dump
    0.25
    -divider
    0.25
    tabs
    0.25
    ENA
    0.25
    èĭ±éĽĦ
    0.25
     tin
    0.24
    åīį
    0.24
    Activations Density 0.266%

    No Known Activations

    This feature has no known activations.