© 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. 141512
    Prev
    Next
    INDEX
    Explanations

    the

    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
     âĨĴ↵↵
    -0.27
    æľīç§į
    -0.26
     sourceMapping
    -0.26
    ILT
    -0.26
     Basel
    -0.25
    addListener
    -0.25
     viewer
    -0.25
     collapsed
    -0.24
    CRT
    -0.24
    bpp
    -0.24
    POSITIVE LOGITS
    ндекÑģ
    0.27
    èĥĮ
    0.27
    specified
    0.26
    æ¯Ķåĸ»
    0.26
    å¤Ł
    0.26
    æ¬ł
    0.25
    texts
    0.25
    ality
    0.25
    ç´
    0.25
    寡
    0.25
    Activations Density 25.243%

    No Known Activations