© 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. 141713
    Prev
    Next
    INDEX
    Explanations

    beginnings

    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
    åı£æ°Ķ
    -0.27
    insn
    -0.27
    isser
    -0.26
    åĿı
    -0.25
    æľīèĥ½åĬĽ
    -0.25
     matcher
    -0.24
    opers
    -0.24
    è¶ĭ
    -0.24
    Ä°N
    -0.24
    _FAR
    -0.24
    POSITIVE LOGITS
    ist
    0.29
    0.28
    ’e
    0.25
     pine
    0.25
     tapped
    0.24
    agem
    0.24
     taps
    0.24
     damned
    0.24
    dr
    0.24
    âĢļ
    0.24
    Activations Density 16.388%

    No Known Activations