© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40704
    Prev
    Next
    INDEX
    Explanations

    characteristics

    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
    urma
    -0.28
     verm
    -0.26
    /fontawesome
    -0.26
    åłĥ
    -0.26
    antium
    -0.26
    åĨĪ
    -0.25
    dro
    -0.25
    æĺ¯ä¸Ģ座
    -0.25
    ä¾Ľåħ»
    -0.25
    ajas
    -0.24
    POSITIVE LOGITS
    è¿Ļæł·åģļ
    0.26
     imposs
    0.26
     пÑĢименениÑı
    0.25
     pose
    0.25
    éĢĻ樣
    0.25
    è¿Ļæł·ä¸Ģ个
    0.25
    è¿Ļæł·çļĦè¯Ŀ
    0.24
     Sylv
    0.24
    onz
    0.24
     posed
    0.24
    Activations Density 1.569%

    No Known Activations