© 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. 40474
    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
     Lambda
    -0.28
    lambda
    -0.27
     lambda
    -0.26
    ermann
    -0.26
     advert
    -0.26
    æ¡Į
    -0.25
     Wedding
    -0.25
    åĬŁ
    -0.25
    &T
    -0.24
     CHARSET
    -0.24
    POSITIVE LOGITS
    .cid
    0.27
     interfer
    0.24
    izon
    0.24
    æľĿé²ľ
    0.24
    iquid
    0.24
    ibur
    0.23
    omat
    0.23
    ê¹Ķ
    0.23
    orical
    0.23
    oad
    0.23
    Activations Density 0.277%

    No Known Activations

    This feature has no known activations.