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. 3914
    Prev
    Next
    INDEX
    Explanations

    is

    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
    nym
    -0.30
     ÑĤоÑĢ
    -0.27
    acja
    -0.27
    ÙĬÙħÙĨ
    -0.25
    é£Ľ
    -0.25
    ungan
    -0.24
     kone
    -0.24
    si
    -0.24
     groot
    -0.24
    é£ŀ
    -0.24
    POSITIVE LOGITS
     incr
    0.26
     Trilogy
    0.26
    olls
    0.26
    ertz
    0.25
    =");↵
    0.24
    allis
    0.23
     assignable
    0.23
    èĥ½è®©
    0.23
    GBT
    0.23
    éĩį度
    0.23
    Activations Density 0.035%

    No Known Activations