Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 53903
    Prev
    Next
    INDEX
    Explanations

    consciousness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lopen
    -0.26
    .Gravity
    -0.26
    .AddItem
    -0.24
     carpets
    -0.24
     Mattis
    -0.24
     Styles
    -0.23
    -Regular
    -0.23
     Principles
    -0.23
     carpet
    -0.23
    ington
    -0.23
    POSITIVE LOGITS
    ANJI
    0.26
    ih
    0.25
    缴å±ŀ
    0.25
    uze
    0.25
    åķŁ
    0.24
    gé
    0.24
    essel
    0.23
    大桥
    0.23
    plotlib
    0.23
    åIJ¯åĬ¨
    0.23
    Activations Density 0.151%

    No Known Activations