© 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. 7789
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    otine
    -0.26
    otte
    -0.25
    ensen
    -0.25
    edException
    -0.23
    ERICA
    -0.23
    UDIO
    -0.23
    lund
    -0.23
     từng
    -0.22
    ening
    -0.22
    owing
    -0.22
    POSITIVE LOGITS
    们çļĦ
    0.26
    ities
    0.26
    /method
    0.24
    ally
    0.24
    .amazonaws
    0.23
     summ
    0.23
    åºĶä»ĺ
    0.23
     tả
    0.23
     liá»ĩu
    0.22
    èij«èĬ¦
    0.22
    Activations Density 2.548%

    No Known Activations