© 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. 19-TRANSCODER-HP
    7. 8106
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢ¡
    -0.30
    éķĴ
    -0.26
    PERT
    -0.25
    Ton
    -0.24
    管çIJĨä¸Ńå¿ĥ
    -0.24
    OPLE
    -0.23
     SIX
    -0.23
    umas
    -0.23
    é¢ĺ主
    -0.23
    dı
    -0.23
    POSITIVE LOGITS
    ä¼ģä¸ļæıIJä¾Ľ
    0.27
    jin
    0.26
    âĢ¢↵↵
    0.25
    loff
    0.24
    inks
    0.24
    otropic
    0.24
    undra
    0.23
    aign
    0.23
    ::$
    0.23
    atis
    0.23
    Activations Density 0.069%

    No Known Activations