© 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. 40423
    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
    isch
    -0.28
    ÃľR
    -0.28
    ãģ¡ãģ¯
    -0.27
     stand
    -0.26
    -pencil
    -0.26
    éļİ
    -0.25
    IRA
    -0.25
     Bonds
    -0.24
    finity
    -0.23
    curities
    -0.23
    POSITIVE LOGITS
    lates
    0.32
    ajan
    0.29
    __:
    0.26
     DST
    0.25
    åĩºä¼ļ
    0.25
     ceremon
    0.25
    Late
    0.25
    èIJ½
    0.24
     ceremonial
    0.24
    åĩ¶
    0.24
    Activations Density 0.178%

    No Known Activations

    This feature has no known activations.