© 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. 8944
    Prev
    Next
    INDEX
    Explanations

    Intention

    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
    mutation
    -0.27
    ModelError
    -0.25
    æĺ¯åĽ½åĨħ
    -0.25
    åľ¨åĽ½åĨħ
    -0.23
     поб
    -0.23
    åIJĦåĽ½
    -0.23
    AFE
    -0.23
    Deal
    -0.22
    *)&
    -0.22
    _DEFINE
    -0.22
    POSITIVE LOGITS
    ance
    0.25
    ayers
    0.24
    ä¹Łå°±æĺ¯è¯´
    0.24
    less
    0.24
    icht
    0.23
    mas
    0.23
    sto
    0.22
    -less
    0.22
    ÑģÑĤвеннÑĭе
    0.22
    full
    0.22
    Activations Density 1.013%

    No Known Activations