© 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. 40004
    Prev
    Next
    INDEX
    Explanations

    Biological classification

    np_max-act · gemini-2.0-flash
    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
    emean
    -0.30
    amed
    -0.28
    ected
    -0.27
     inher
    -0.27
    gio
    -0.27
     Baptist
    -0.27
     endian
    -0.26
    AMED
    -0.26
    ymm
    -0.26
     quanto
    -0.26
    POSITIVE LOGITS
    _plural
    0.28
    åĴĮ个人
    0.27
    ä¸ĢåľĪ
    0.26
    ä»Ģä¹Īä¸ľè¥¿
    0.25
    è¿Ļ个人
    0.24
    ä¸Ģ件äºĭæĥħ
    0.24
    >((
    0.24
    两家
    0.24
    å°±æĥ³
    0.24
     refer
    0.24
    Activations Density 0.952%

    No Known Activations