© 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. 41778
    Prev
    Next
    INDEX
    Explanations

    Math formulas

    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
    ESIS
    -0.30
     meanwhile
    -0.28
     whilst
    -0.27
    ymes
    -0.26
    systems
    -0.26
    ası
    -0.26
    Leaks
    -0.25
    èµ°è¿Ľ
    -0.25
    odesk
    -0.25
    spaces
    -0.25
    POSITIVE LOGITS
    reuse
    0.28
     rm
    0.27
    acer
    0.27
    ages
    0.27
    èĻ¹æ¡¥
    0.25
     ↵↵
    0.25
    _mm
    0.25
    港åı£
    0.25
    èĤ¡
    0.24
    è®¤çŁ¥
    0.24
    Activations Density 0.583%

    No Known Activations