© 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. 130592
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
    HER
    -0.27
    avel
    -0.25
    AVING
    -0.24
    bens
    -0.24
     Build
    -0.24
    æĮĩå®ļ
    -0.24
    ponsible
    -0.24
    çī©çIJĨåѦ
    -0.24
    建
    -0.24
    aison
    -0.24
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.31
    åĩºçİ°åľ¨
    0.29
     topical
    0.27
    åĪ«è¯´
    0.26
    ä½ľä¸ºä¸Ģ个
    0.26
    ieux
    0.25
    amus
    0.25
    emma
    0.25
    æµĨ
    0.25
    mere
    0.25
    Activations Density 76.075%

    No Known Activations