© 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. 20-TRANSCODER-HP
    7. 141332
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.30
    ritz
    -0.26
    /*----------------------------------------------------------------
    -0.26
     gover
    -0.24
    $
    -0.24
     Comfort
    -0.24
     Hann
    -0.24
    è¿Ļæĺ¯åĽłä¸º
    -0.24
     Memor
    -0.24
     proved
    -0.24
    POSITIVE LOGITS
    Rnd
    0.29
    å¥Ĺ
    0.28
     Sheikh
    0.28
    \grid
    0.27
    ertino
    0.27
     confuse
    0.26
    umbles
    0.26
    altar
    0.25
    ascar
    0.24
    enge
    0.24
    Activations Density 15.371%

    No Known Activations