© 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. 141885
    Prev
    Next
    INDEX
    Explanations

    Relative pronouns

    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
    ãģĵãĤĵ
    -0.27
    .Q
    -0.26
    ãģ¯ãģĺ
    -0.26
    -ahead
    -0.26
    蹩
    -0.25
    åı¯æĥľ
    -0.25
    伤害
    -0.25
    ,Q
    -0.24
     riff
    -0.24
    ahead
    -0.24
    POSITIVE LOGITS
    ijo
    0.29
    ToSelector
    0.28
    acho
    0.27
    涡
    0.25
    .childNodes
    0.25
    atom
    0.23
     getline
    0.23
    èŀ¯
    0.23
    UT
    0.23
    edo
    0.23
    Activations Density 4.792%

    No Known Activations