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. 4054
    Prev
    Next
    INDEX
    Explanations

    technical and computer content

    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
    icer
    -0.28
    ople
    -0.27
    åݨ
    -0.26
    icrosoft
    -0.25
    梯
    -0.25
    ards
    -0.25
    æĿ¾
    -0.25
     Pare
    -0.24
     probably
    -0.24
     loos
    -0.24
    POSITIVE LOGITS
    Topology
    0.27
     Flooring
    0.26
    .Dao
    0.26
    chin
    0.25
     affirm
    0.25
     Boundary
    0.25
     Assault
    0.25
    _ring
    0.25
    Chess
    0.25
    fra
    0.25
    Activations Density 0.005%

    No Known Activations