© 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. 63848
    Prev
    Next
    INDEX
    Explanations

    Text snippets from data sources

    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
    ASI
    -0.29
    åıĺ
    -0.26
     mindful
    -0.26
     teardown
    -0.24
     Convers
    -0.24
     société
    -0.24
    glich
    -0.24
     modeled
    -0.24
     letz
    -0.24
    社
    -0.23
    POSITIVE LOGITS
    è·Łä»ĸ
    0.28
    ĽĦ
    0.27
    è·Łå¥¹
    0.27
    ä»Ģä¹Īåij¢
    0.25
    torrent
    0.25
    ÃŃt
    0.24
    egr
    0.24
    ahoo
    0.24
    OwnProperty
    0.23
    uda
    0.23
    Activations Density 2.460%

    No Known Activations