© 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. 41381
    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
    éĩįè¦ģ
    -0.29
    æĥħ
    -0.28
    èį¯ä¸ļ
    -0.26
     Maker
    -0.26
     Locations
    -0.25
    -Level
    -0.25
    å±ŀ
    -0.25
     ny
    -0.24
    æĭĽå¾ħ
    -0.24
     Publish
    -0.24
    POSITIVE LOGITS
    æľºåĬ¨è½¦
    0.28
     versions
    0.27
     leftovers
    0.27
    åĮħ袱
    0.27
    å®Ī
    0.26
    çīĮåŃIJ
    0.25
     motor
    0.25
    avor
    0.25
    itag
    0.25
    æijĩ
    0.25
    Activations Density 0.213%

    No Known Activations

    This feature has no known activations.