© 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. 18-TRANSCODER-HP
    7. 89257
    Prev
    Next
    INDEX
    Explanations

    hard work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缸è¾ĥ
    -0.31
    念
    -0.26
    kest
    -0.26
    èĥĮ
    -0.25
     dém
    -0.25
    yscale
    -0.25
    çĿ¹
    -0.24
    缸è§ģ
    -0.24
    å¥ļ
    -0.24
    论
    -0.24
    POSITIVE LOGITS
    Hur
    0.33
    hunter
    0.28
     underground
    0.28
    ç©Ĺ
    0.28
    ove
    0.27
     Hur
    0.27
    åħ±åIJĮåĬªåĬĽ
    0.26
     Fry
    0.25
     accomplishment
    0.25
    pulse
    0.25
    Activations Density 57.687%

    No Known Activations