© 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. 130555
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    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°ıèħ¿
    -0.27
    æľºæŀĦ
    -0.26
    èį·
    -0.26
    åħij
    -0.25
    ç»ĪçĤ¹
    -0.25
    鬯
    -0.25
    kee
    -0.24
    /MIT
    -0.24
    éĺ³
    -0.23
    abar
    -0.23
    POSITIVE LOGITS
    atz
    0.26
     capture
    0.26
    atus
    0.25
    еÑĩно
    0.24
     RVA
    0.24
    (sc
    0.24
    çĻ¾äº¿
    0.23
    .Embed
    0.23
    vincia
    0.23
    :num
    0.23
    Activations Density 13.139%

    No Known Activations