© 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. 6800
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    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
    volution
    -0.28
    anye
    -0.26
     DialogInterface
    -0.26
    αι
    -0.25
    toPromise
    -0.24
    æª
    -0.24
     camel
    -0.23
    accuracy
    -0.23
    vester
    -0.23
    omics
    -0.23
    POSITIVE LOGITS
    ï¼ļ↵↵
    0.33
    :↵↵
    0.33
    ï¼ļ↵
    0.32
    :↵
    0.30
    ï¼ļ</
    0.29
    ä¾ĭå¦Ĥ
    0.29
    示
    0.28
    ï¼ļ%
    0.28
    ä¾ĭ
    0.28
    å¦Ĥä¸ĭ
    0.28
    Activations Density 0.257%

    No Known Activations