© 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. 40135
    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
     clone
    -0.30
     expend
    -0.28
     ÎĶ
    -0.27
     contr
    -0.27
     balance
    -0.26
    _BAL
    -0.26
    Mes
    -0.26
    çĽĬ
    -0.26
    ÎĶ
    -0.26
    adal
    -0.25
    POSITIVE LOGITS
    ç»ĨåĮĸ
    0.26
    åĽłä¸ºä»ĸ们
    0.25
    港åĮº
    0.25
    论è¯ģ
    0.24
    æİĮ
    0.24
    ingham
    0.24
    .getProperties
    0.23
    롯
    0.23
    emony
    0.23
    atile
    0.23
    Activations Density 0.896%

    No Known Activations

    This feature has no known activations.