© 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. 39475
    Prev
    Next
    INDEX
    Explanations

    addition

    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
    atat
    -0.25
    ÙĪغ
    -0.25
     muc
    -0.24
    rax
    -0.24
    主管
    -0.24
    è½°çĤ¸
    -0.24
    ä¸Ģæŀ¶
    -0.23
    duct
    -0.23
    ä¸Ģæ¢Ŀ
    -0.23
    è®°å¿ĨåĬĽ
    -0.23
    POSITIVE LOGITS
     informal
    0.29
    elsey
    0.28
    æľĢå¿«çļĦ
    0.27
    èĪ¶
    0.27
    å¯ĵ
    0.26
    roe
    0.25
    /DD
    0.25
    implicit
    0.24
     Malcolm
    0.24
    iefs
    0.24
    Activations Density 0.990%

    No Known Activations