© 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. 107780
    Prev
    Next
    INDEX
    Explanations

    code and file processing

    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
     lo
    -0.31
    inges
    -0.30
     Sphere
    -0.26
    å¼ĢçĿĢ
    -0.26
    loe
    -0.25
    建设åĴĮ
    -0.25
    Ä»
    -0.24
    ][
    -0.24
    ientes
    -0.24
    åij¼ãģ³
    -0.24
    POSITIVE LOGITS
    within
    0.39
     inside
    0.39
     within
    0.38
    inside
    0.35
    among
    0.35
    contained
    0.34
     Within
    0.33
     contained
    0.33
    Within
    0.32
    åľ¨éĩĮéĿ¢
    0.32
    Activations Density 59.477%

    No Known Activations