© 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. 39805
    Prev
    Next
    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    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
    éŨæĪ·ç½ijç«Ļ
    -0.26
    SCALE
    -0.26
    CEPTION
    -0.26
    è¹ĩ
    -0.25
     intercepted
    -0.25
     Satellite
    -0.25
    BAD
    -0.24
     moth
    -0.24
    creenshot
    -0.24
    åĪĨæľŁ
    -0.24
    POSITIVE LOGITS
    次
    0.33
    çł´
    0.29
    次æķ°
    0.29
    łģ
    0.27
    æľ¯
    0.26
    è¾ķ
    0.26
    -eff
    0.25
     ieee
    0.25
    æĢģ
    0.24
    èIJ½
    0.24
    Activations Density 0.603%

    No Known Activations