© 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. 142380
    Prev
    Next
    INDEX
    Explanations

    Technical and scientific texts

    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
    iquid
    -0.27
    ANGES
    -0.27
    Attrs
    -0.26
    isto
    -0.25
    _controls
    -0.25
    ursive
    -0.25
    ives
    -0.25
    ias
    -0.25
    以éĺ²
    -0.25
    ubbles
    -0.24
    POSITIVE LOGITS
     Neighborhood
    0.29
    nth
    0.27
     Cons
    0.27
    éŀį
    0.27
     cons
    0.26
    .animations
    0.25
     neighborhood
    0.25
    é¹Ĭ
    0.24
     Origin
    0.24
    nb
    0.24
    Activations Density 0.667%

    No Known Activations