© 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. 39463
    Prev
    Next
    INDEX
    Explanations

    Emailing and friends

    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
    Negative Logits
    adh
    -0.29
    è¿Ľä¸ĢæŃ¥
    -0.27
     virgin
    -0.27
    ä»°
    -0.27
    æĸĩåĮĸåĴĮ
    -0.26
    åŃĹæ¯į
    -0.26
    åĬłåħ¥
    -0.26
    ophil
    -0.25
    inks
    -0.25
     'č↵
    -0.25
    POSITIVE LOGITS
    ennen
    0.30
     distributes
    0.27
    æıĴ座
    0.26
    .Align
    0.26
    ebb
    0.26
     HEX
    0.25
     distribute
    0.25
    åıijæĶ¾
    0.25
    åħ«å¤§
    0.25
     Distrib
    0.24
    Activations Density 0.110%

    No Known Activations