© 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. 41446
    Prev
    Next
    INDEX
    Explanations

    efficiency

    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
    grad
    -0.29
    åIJĮä»ģ
    -0.26
    awai
    -0.25
    æĹıèĩªæ²»å·ŀ
    -0.25
    illas
    -0.25
    habi
    -0.25
    pieces
    -0.24
    uiten
    -0.24
    鸥
    -0.24
    acción
    -0.24
    POSITIVE LOGITS
     Honour
    0.30
    ised
    0.28
     Pref
    0.27
     Cone
    0.27
    ãģĵ
    0.27
     tam
    0.27
     confl
    0.27
    éľĩ
    0.26
    令
    0.26
    ized
    0.25
    Activations Density 0.738%

    No Known Activations