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. 1692
    Prev
    Next
    INDEX
    Explanations

    numbers and comparisons

    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
    å¥ij
    -0.27
    oom
    -0.26
    åIJĪèµĦ
    -0.25
     parted
    -0.24
    stitution
    -0.24
    oples
    -0.24
    ä¸Ģéģį
    -0.24
    iedades
    -0.24
    ight
    -0.23
    powers
    -0.23
    POSITIVE LOGITS
    çļĦçģµéŃĤ
    0.29
    æĪĸå¤ļ
    0.25
    Vo
    0.25
    abus
    0.25
    Ñīи
    0.25
    æĦį
    0.24
    åı¯çĸij
    0.24
    yet
    0.24
    ft
    0.24
    ToOne
    0.24
    Activations Density 0.018%

    No Known Activations