© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7404
    Prev
    Next
    INDEX
    Explanations

    Educational institutions

    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
     Funding
    -0.27
     funding
    -0.27
    å¯ĨåĪĩ
    -0.27
    åĪ°åºķæĺ¯
    -0.26
    è¶Ł
    -0.25
    whether
    -0.24
    ãģĦãģĨ
    -0.24
    adder
    -0.24
    erved
    -0.24
    å¿Į
    -0.24
    POSITIVE LOGITS
    ialis
    0.33
     beÄŁen
    0.27
    posables
    0.27
    ÑĮе
    0.25
    常åĬ¡
    0.24
    shit
    0.24
    ium
    0.24
    grupo
    0.23
     wholes
    0.23
    æĺ´
    0.23
    Activations Density 0.005%

    No Known Activations