© 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. 20-TRANSCODER-HP
    7. 107357
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJįçīĮ
    -0.27
    ror
    -0.26
    æŦ
    -0.26
    徨
    -0.25
     posters
    -0.25
    姬
    -0.24
    OD
    -0.24
    ical
    -0.23
    ock
    -0.23
    ÙĪÙĤع
    -0.23
    POSITIVE LOGITS
    ippi
    0.31
    ansas
    0.30
    ectl
    0.27
    Coder
    0.27
    ensively
    0.27
    Https
    0.26
    renders
    0.25
    åĪĨç±»
    0.25
    atee
    0.25
    etch
    0.24
    Activations Density 8.981%

    No Known Activations