© 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. 142040
    Prev
    Next
    INDEX
    Explanations

    Programming

    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
     —↵↵
    -0.29
    ément
    -0.27
    æīįç®Ĺ
    -0.26
    åī¯æĢ»è£ģ
    -0.26
    æīįä¼ļ
    -0.25
    常åĬ¡åī¯
    -0.25
    æĹ¢æľī
    -0.24
    æīįæľī
    -0.24
    =#
    -0.24
    æ¯ĭ
    -0.24
    POSITIVE LOGITS
    (Editor
    0.28
    Resizable
    0.26
    /editor
    0.26
    ãģªãģ©ãģ§
    0.25
    ogl
    0.25
     known
    0.24
    |unique
    0.24
     eyes
    0.24
    æIJŃ
    0.23
    çľĭä½ł
    0.23
    Activations Density 17.222%

    No Known Activations