© 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. 88978
    Prev
    Next
    INDEX
    Explanations

    Mentions years

    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
     pom
    -0.29
     excl
    -0.25
    ä¿ĺ
    -0.25
    ä»Ĩ
    -0.25
     exclus
    -0.25
     exclude
    -0.24
    åıĺåİĭ
    -0.24
     Station
    -0.24
    losures
    -0.24
     Pom
    -0.23
    POSITIVE LOGITS
    MUX
    0.30
    otte
    0.29
    åİ»æī¾
    0.28
    auge
    0.28
    yme
    0.27
    æł¹åºķ
    0.27
    ystack
    0.25
    roup
    0.25
    atron
    0.25
    óg
    0.24
    Activations Density 4.598%

    No Known Activations