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. 7-TRANSCODER-HP
    4. 15425
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭľ
    -0.28
    ymoon
    -0.25
    欢è¿İ
    -0.25
    _HAL
    -0.24
     bow
    -0.24
    Om
    -0.24
    æĪij没æľī
    -0.24
     rum
    -0.24
    runner
    -0.23
     peri
    -0.23
    POSITIVE LOGITS
    icum
    0.28
    orate
    0.27
    ingly
    0.25
    ought
    0.25
    adden
    0.25
    gia
    0.24
    .lb
    0.24
     additional
    0.23
    oire
    0.23
    çĸij
    0.23
    Activations Density 0.001%

    No Known Activations