© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    limit

    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
    bedo
    -0.26
    æ¯Ķåĸ»
    -0.25
    æĦŁåı¹
    -0.24
    agog
    -0.24
    æĹłç§ģ
    -0.23
    alia
    -0.23
    ea
    -0.23
    æ¶Įçİ°åĩº
    -0.22
    è¸Ĭè·ĥ
    -0.22
    rap
    -0.22
    POSITIVE LOGITS
    ä½ıäºĨ
    0.29
    æĿĵ
    0.25
    trag
    0.24
     beyond
    0.24
    bars
    0.24
     freedom
    0.24
    Reached
    0.24
     far
    0.24
    /control
    0.23
    sto
    0.23
    Activations Density 1.087%

    No Known Activations