© 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. 41543
    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
    è¶ħè¶Ĭ
    -0.28
    cratch
    -0.27
    iphy
    -0.26
    quarters
    -0.25
    Memory
    -0.24
    ä¸ĭæ»ij
    -0.24
    _COMM
    -0.24
     stead
    -0.24
    stead
    -0.24
    ëĭ¥
    -0.24
    POSITIVE LOGITS
    çļĦä¸Ģ款
    0.27
    ä¸Ģç§į
    0.27
    çļĦä¸Ģç§į
    0.26
    ä¸Ŀä¸Ŀ
    0.26
    gw
    0.26
     conservative
    0.25
     unf
    0.25
    tn
    0.25
    éŃĦ
    0.25
    ä¸įè§ģ
    0.24
    Activations Density 4.023%

    No Known Activations

    This feature has no known activations.