© 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. 7590
    Prev
    Next
    INDEX
    Explanations

    News, reports, studies

    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
     unloaded
    -0.30
    benh
    -0.27
    jang
    -0.26
    uil
    -0.26
    bell
    -0.25
     Kurd
    -0.24
    -wheel
    -0.24
    ä¹łæĥ¯äºĨ
    -0.24
    лиÑĤ
    -0.23
    wards
    -0.23
    POSITIVE LOGITS
     sc
    0.25
    еÑģÑģ
    0.24
    ç¨ĭ度
    0.24
    æµĬ
    0.23
     Pri
    0.23
    Concurrency
    0.23
    é»Ħæ²³
    0.23
    åı¯è§ģ
    0.23
    Recogn
    0.23
     IRS
    0.22
    Activations Density 0.035%

    No Known Activations