© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    Requirements, instructions, or conditions

    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
     meanwhile
    -0.27
     analyse
    -0.27
    ogram
    -0.26
     lagi
    -0.25
    趴
    -0.24
    çIJı
    -0.24
    :variables
    -0.24
    åĩºå¢ĥ
    -0.24
     favourable
    -0.24
    亹
    -0.23
    POSITIVE LOGITS
     Less
    0.28
    ypo
    0.26
    -us
    0.26
    -transitional
    0.24
    é»ijçĻ½
    0.24
    .throw
    0.24
     restricted
    0.24
     less
    0.23
    ().__
    0.23
    è¿Ļè¾¹
    0.23
    Activations Density 0.020%

    No Known Activations