© 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. 63690
    Prev
    Next
    INDEX
    Explanations

    General internet content

    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
    -width
    -0.27
    quartered
    -0.26
    注éĶĢ
    -0.26
    寰
    -0.25
    éĭĨ
    -0.24
    鸢
    -0.24
    Fonts
    -0.24
    ?),
    -0.23
    living
    -0.23
    æľīæĿĥ
    -0.23
    POSITIVE LOGITS
    adc
    0.29
    avor
    0.28
    pos
    0.28
    ANE
    0.28
    POS
    0.27
    ccb
    0.27
     bridge
    0.26
    abb
    0.26
    aths
    0.26
    acements
    0.26
    Activations Density 16.767%

    No Known Activations