© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41764
    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
    Negative Logits
    å·«
    -0.29
    深交
    -0.28
    èļ±
    -0.26
    lesc
    -0.25
    ompiler
    -0.25
    磮
    -0.24
    Sources
    -0.24
    جاÙĦ
    -0.24
     figura
    -0.24
    æĥħåĨµæĿ¥çľĭ
    -0.23
    POSITIVE LOGITS
    CX
    0.31
    uit
    0.28
    èĻij
    0.26
    çĶ²
    0.25
    ĵį
    0.25
    anking
    0.25
    _fx
    0.25
    éĺµéĺµ
    0.24
    åıĭ
    0.24
    _POST
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.