© 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. 39594
    Prev
    Next
    INDEX
    Explanations

    Transfer of leadership

    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
    MISS
    -0.28
    assy
    -0.27
    æ°°
    -0.27
    met
    -0.26
     bÄĻdÄĻ
    -0.25
     gm
    -0.24
    ass
    -0.24
    ary
    -0.24
    çĿ¹
    -0.24
    uto
    -0.24
    POSITIVE LOGITS
    èĪªéģĵ
    0.27
    cord
    0.27
    Lane
    0.27
     Hayden
    0.26
    /host
    0.26
    ói
    0.26
    otal
    0.25
    ạp
    0.25
    深交
    0.25
    é¼ĵ
    0.25
    Activations Density 1.172%

    No Known Activations