© 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. 108006
    Prev
    Next
    INDEX
    Explanations

    1

    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
    egration
    -0.28
    egr
    -0.27
    ·æĸ°
    -0.27
    追æ±Ĥ
    -0.27
    æł¼
    -0.27
    为æѤ
    -0.26
    縮
    -0.25
     congr
    -0.25
    ({_
    -0.25
    ¬´
    -0.24
    POSITIVE LOGITS
    ople
    0.25
    .HandleFunc
    0.25
     underwater
    0.25
     Bedroom
    0.25
    haled
    0.24
    è¾°
    0.24
     Under
    0.23
    mutable
    0.23
    iri
    0.23
    æĬĦ
    0.23
    Activations Density 6.953%

    No Known Activations