© 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. 107887
    Prev
    Next
    INDEX
    Explanations

    opportunities

    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
    ering
    -0.29
    itud
    -0.26
    åĬŀåħ¬å®¤
    -0.25
    pliant
    -0.25
    rollers
    -0.25
    avy
    -0.25
    vision
    -0.25
    æŃ¤äºº
    -0.24
    vida
    -0.24
    çľģå§Ķ
    -0.24
    POSITIVE LOGITS
    inte
    0.27
     neighbouring
    0.25
    /kubernetes
    0.25
    (par
    0.24
    .cuda
    0.24
    å®ŀåľ¨æĺ¯å¤ª
    0.23
    bout
    0.23
     carved
    0.22
    ipe
    0.22
    å¡ŀ
    0.22
    Activations Density 16.151%

    No Known Activations