© 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. 8378
    Prev
    Next
    INDEX
    Explanations

    code and equations

    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
     banking
    -0.25
    åIJ«
    -0.25
     Banking
    -0.25
    åħ¨åĮº
    -0.24
     cast
    -0.24
    iore
    -0.24
     test
    -0.23
    Test
    -0.23
     screenshots
    -0.23
    éĻ
    -0.23
    POSITIVE LOGITS
    __[
    0.28
    depend
    0.27
    (resources
    0.26
     kiến
    0.26
    icularly
    0.25
    .readAs
    0.25
    åijĪ
    0.24
    毫æĹł
    0.24
    _brand
    0.24
    [color
    0.23
    Activations Density 0.119%

    No Known Activations