© 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. 130760
    Prev
    Next
    INDEX
    Explanations

    state

    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
     push
    -0.28
     Occup
    -0.27
    push
    -0.27
    ACY
    -0.27
    bel
    -0.27
     alk
    -0.27
     al
    -0.26
    UST
    -0.26
     Tang
    -0.26
     es
    -0.26
    POSITIVE LOGITS
    conde
    0.26
    ateway
    0.25
    ophobic
    0.24
    æĸĩåĮĸåĴĮ
    0.24
    amel
    0.24
    è¿İåIJĪ
    0.23
    asive
    0.23
    adora
    0.23
    minute
    0.23
    ForgeryToken
    0.22
    Activations Density 24.812%

    No Known Activations