© 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. 9-TRANSCODER-HP
    7. 29637
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    天ä¸ĭ
    -0.27
    hani
    -0.25
    ilage
    -0.24
    {id
    -0.24
    olver
    -0.24
    emp
    -0.24
    holm
    -0.24
    æĢı
    -0.24
    稳åģ¥
    -0.24
    æĸĩåĮĸåĴĮ
    -0.23
    POSITIVE LOGITS
    åįĥåħĥ
    0.28
    pesan
    0.26
    纺
    0.26
     yerleÅŁ
    0.25
    -inst
    0.25
    ":"'
    0.25
    ä¸įæĩĪ
    0.25
    å¯Ĵ
    0.24
    oref
    0.24
     Bureau
    0.24
    Activations Density 0.744%

    No Known Activations