© 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. 130108
    Prev
    Next
    INDEX
    Explanations

    difficulty

    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
    å°¼äºļ
    -0.28
    oto
    -0.26
    å¾Ī好çļĦ
    -0.25
    åijµæĬ¤
    -0.25
    EDGE
    -0.24
    isms
    -0.24
    æıIJåĪ°
    -0.24
    çĤ¹ç¼Ģ
    -0.24
    enn
    -0.24
    nten
    -0.23
    POSITIVE LOGITS
    /conf
    0.27
    åĢĮ
    0.26
    ¤í
    0.25
    太快
    0.25
    fully
    0.25
    arious
    0.24
     bey
    0.24
    ãģĵãĤĵ
    0.24
    ForObject
    0.23
     introductory
    0.23
    Activations Density 14.323%

    No Known Activations