© 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. 142160
    Prev
    Next
    INDEX
    Explanations

    to

    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
    æĦıåij³
    -0.27
     shade
    -0.26
    示æĦı
    -0.25
    æIJª
    -0.25
     blat
    -0.25
     EITHER
    -0.24
    åºĬä¸Ĭ
    -0.24
    .epoch
    -0.23
    .mean
    -0.23
     öl
    -0.23
    POSITIVE LOGITS
    urvey
    0.32
    linkplain
    0.29
     itself
    0.28
    ertos
    0.27
     universally
    0.27
    çł´è£Ĥ
    0.26
    æł¡åĽŃ
    0.26
     themselves
    0.25
    unker
    0.25
     surveyed
    0.25
    Activations Density 14.275%

    No Known Activations