© 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. 130012
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    èĭ´
    -0.26
    assets
    -0.25
     seal
    -0.25
    便åĪ©
    -0.24
     Curso
    -0.24
     Himself
    -0.24
     Cush
    -0.23
    assist
    -0.23
    TERM
    -0.23
    Ti
    -0.23
    POSITIVE LOGITS
    edly
    0.26
    ISE
    0.26
     slower
    0.26
     gibi
    0.26
    hma
    0.26
    ä¼ĺ
    0.25
    ARC
    0.25
    åİ»åģļ
    0.24
    æ¹¾åĮº
    0.24
    zd
    0.24
    Activations Density 3.271%

    No Known Activations