© 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. 27-TRANSCODER-HP
    7. 57427
    Prev
    Next
    INDEX
    Explanations

    file paths/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplast
    -0.26
     reading
    -0.26
     Ben
    -0.24
    itung
    -0.24
    _na
    -0.24
     darauf
    -0.23
    .Foundation
    -0.23
    å¨ģ
    -0.23
    :?
    -0.23
    Reading
    -0.23
    POSITIVE LOGITS
     drag
    0.29
    \Lib
    0.28
    pty
    0.27
    ä¼ĺ
    0.26
    letes
    0.26
    绾
    0.25
    haul
    0.25
    linger
    0.25
     hustle
    0.25
     ******************************************************************************↵
    0.25
    Activations Density 0.001%

    No Known Activations