© 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. 41612
    Prev
    Next
    INDEX
    Explanations

    Body image and appearance

    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
    /styles
    -0.28
    ноп
    -0.26
     Ñģобой
    -0.26
    .offsetHeight
    -0.26
    ransition
    -0.25
    AdminController
    -0.25
    velte
    -0.25
    ship
    -0.24
    éĹ¼
    -0.24
    VALID
    -0.24
    POSITIVE LOGITS
    èµĦ
    0.28
    å¸ĥé²ģ
    0.26
    å¥Ĺé¤IJ
    0.26
     subs
    0.26
     slugg
    0.25
    ä¼ł
    0.24
    éĢł
    0.24
    init
    0.24
     Pres
    0.24
    omet
    0.24
    Activations Density 0.194%

    No Known Activations