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. 27-TRANSCODER-HP
    4. 785
    Prev
    Next
    INDEX
    Explanations

    request

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ijke
    -0.30
     fluid
    -0.28
    udies
    -0.26
    次
    -0.26
     liquid
    -0.24
    abez
    -0.24
    éĮĦ
    -0.23
    åĩĢå̼
    -0.23
     adequate
    -0.23
    æĹ¶æĬ¥
    -0.23
    POSITIVE LOGITS
     primitives
    0.32
     request
    0.28
     send
    0.28
    å¾Ģè¿Ķ
    0.27
     notifications
    0.27
    tero
    0.27
    请æ±Ĥ
    0.26
     Entire
    0.26
     URL
    0.26
     messages
    0.26
    Activations Density 0.062%

    No Known Activations