© 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. 14-TRANSCODER-HP
    7. 40170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anness
    -0.28
    indow
    -0.28
    æĦıåIJij
    -0.26
    unnel
    -0.25
    ernel
    -0.25
    ä½į
    -0.24
    localized
    -0.24
    à¹ģà¸Ľà¸¥
    -0.24
     acc
    -0.24
    uggestion
    -0.24
    POSITIVE LOGITS
    Contr
    0.27
     Contr
    0.26
    Je
    0.26
    Comfort
    0.25
    ahr
    0.25
    饱åĴĮ
    0.25
    æīĢæıIJä¾ĽçļĦ
    0.25
    çļĦä¸įåIJĮ
    0.24
    æŁ¥éĺħ
    0.24
    rams
    0.24
    Activations Density 0.079%

    No Known Activations

    This feature has no known activations.