© 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. 41447
    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
    .subscribe
    -0.28
    agna
    -0.27
     Rit
    -0.27
     Patron
    -0.25
    å·¥åķĨ
    -0.25
    马åħĭ
    -0.25
     Affero
    -0.25
     Liter
    -0.24
    idel
    -0.24
    alars
    -0.24
    POSITIVE LOGITS
    æıIJåĩºçļĦ
    0.27
    缸åħ³äººåijĺ
    0.27
    çŃĿ
    0.27
    èĢĮåıĪ
    0.26
    Versions
    0.25
    åĭĩ
    0.24
     tents
    0.24
     bumped
    0.24
    ç²½
    0.24
     tamb
    0.24
    Activations Density 0.860%

    No Known Activations

    This feature has no known activations.