© 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. 141143
    Prev
    Next
    INDEX
    Explanations

    when

    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
    ä¾Ŀæ³ķ追究
    -0.27
    éģij
    -0.25
    Cor
    -0.24
    çĤ¹äºĨçĤ¹å¤´
    -0.24
     Momentum
    -0.24
    Nut
    -0.23
    åļ¼
    -0.23
    ead
    -0.23
    bounce
    -0.23
     Lorem
    -0.23
    POSITIVE LOGITS
    èĤĦ
    0.30
     spanning
    0.30
    -span
    0.28
     scenario
    0.27
    å¿ĥæĦı
    0.26
    -used
    0.26
    \Db
    0.26
    âĬ¿
    0.26
    amba
    0.25
    issen
    0.24
    Activations Density 20.892%

    No Known Activations