© 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. 62960
    Prev
    Next
    INDEX
    Explanations

    Technical/unstructured text

    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
    vig
    -0.26
    pas
    -0.23
    iline
    -0.23
     Hacker
    -0.22
    NIL
    -0.22
     proced
    -0.22
    bé
    -0.22
    å¸Ĥ
    -0.22
    inus
    -0.22
    LAG
    -0.21
    POSITIVE LOGITS
    istani
    0.25
    istan
    0.23
    åŀļ
    0.23
    anner
    0.22
    è¾ĸåĮº
    0.22
    bourne
    0.21
    obao
    0.21
    æĢ»éĩı
    0.21
    ANNER
    0.21
    ç»Ī身
    0.21
    Activations Density 91.405%

    No Known Activations