© 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. 41226
    Prev
    Next
    INDEX
    Explanations

    .apache

    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
    羣çļ®
    -0.28
     ç¤
    -0.25
     pace
    -0.25
    é¢Ĩ
    -0.25
    itar
    -0.24
     walls
    -0.24
    cape
    -0.24
    cs
    -0.24
     drove
    -0.24
     cape
    -0.24
    POSITIVE LOGITS
    zung
    0.28
    çĶ·å¥³
    0.28
    è¦ĨçĽĸ
    0.27
    åĪ°åºķæĺ¯
    0.27
    acas
    0.26
    Shadow
    0.26
    天çĦ¶
    0.26
    åıĤ
    0.25
    egen
    0.25
    byname
    0.25
    Activations Density 0.936%

    No Known Activations