© 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. 41377
    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
    éĩįå¤į
    -0.28
    EDIA
    -0.28
    tml
    -0.27
    @"
    -0.26
    .Dot
    -0.26
    æĮ¥
    -0.25
    æľīä¸Ģ
    -0.24
    æ³°å±±
    -0.24
    graphics
    -0.24
    è£ģ
    -0.24
    POSITIVE LOGITS
    媳å¦ĩ
    0.25
    ÃŃst
    0.24
     confidently
    0.23
    迤
    0.23
    ivamente
    0.23
     Anch
    0.22
    æ±
    0.22
    ramework
    0.22
     Lesb
    0.22
     confessed
    0.22
    Activations Density 0.448%

    No Known Activations

    This feature has no known activations.