© 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. 141561
    Prev
    Next
    INDEX
    Explanations

    murder

    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
    rit
    -0.32
    _magic
    -0.27
    èĭĪ
    -0.26
    oproject
    -0.25
    rink
    -0.24
     Bach
    -0.23
    åĽĽçº§
    -0.23
    óst
    -0.23
     QDialog
    -0.23
    âĢ¦”↵↵
    -0.22
    POSITIVE LOGITS
    ometer
    0.25
     lurking
    0.25
     gene
    0.25
    åģļçļĦ
    0.25
    /Private
    0.24
    ä¸ĭæīĭ
    0.24
     happening
    0.24
    ä¹Łä¸įæĥ³
    0.24
    ä¼ļéķ¿
    0.24
    åıijçĶŁåľ¨
    0.23
    Activations Density 15.992%

    No Known Activations