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. 0-TRANSCODER-HP
    4. 201
    Prev
    Next
    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elize
    -0.26
     nú
    -0.26
    .getLatitude
    -0.26
    pac
    -0.25
    çĭ¸
    -0.24
    lds
    -0.23
    ihar
    -0.23
    efs
    -0.23
     pot
    -0.23
    té
    -0.23
    POSITIVE LOGITS
     into
    0.27
    gram
    0.27
    agram
    0.26
    Into
    0.24
    ayers
    0.24
    noop
    0.24
    Times
    0.24
    ÙĪØ§Ø¨
    0.24
    诺
    0.24
     Into
    0.23
    Activations Density 5.267%

    No Known Activations