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. 146819
    Prev
    Next
    INDEX
    Explanations

    District of Columbia, contributions

    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
    lets
    -0.29
    engl
    -0.29
    YP
    -0.29
    åĿIJ
    -0.27
    .ny
    -0.26
    nik
    -0.26
    ËĮ
    -0.25
    .PropertyType
    -0.25
    çĮİ
    -0.25
    åºŁå¼ĥçī©
    -0.25
    POSITIVE LOGITS
    amous
    0.27
    +"]
    0.25
    KHR
    0.25
    å®ŀåľ¨
    0.25
    rium
    0.25
     Baths
    0.25
     Pics
    0.24
    borg
    0.24
    avian
    0.24
    metics
    0.24
    Activations Density 0.055%

    No Known Activations