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. 53842
    Prev
    Next
    INDEX
    Explanations

    medical conditions and infections

    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
    褡
    -0.27
     Serg
    -0.26
    ijľ
    -0.24
    eworld
    -0.24
     Cotton
    -0.23
    æĸ°åŁİ
    -0.23
     sung
    -0.23
     monastery
    -0.23
     corners
    -0.23
    ULER
    -0.23
    POSITIVE LOGITS
    cdf
    0.31
    åĪ©
    0.28
    xAF
    0.28
    CAD
    0.28
     vs
    0.27
    odom
    0.26
    ç«ĭ
    0.25
     versus
    0.25
     challenge
    0.25
    Leg
    0.24
    Activations Density 0.048%

    No Known Activations