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. 53327
    Prev
    Next
    INDEX
    Explanations

    foundation

    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
    åĮħ
    -0.31
    доб
    -0.27
    Cancelable
    -0.25
    -under
    -0.24
    onian
    -0.24
    -script
    -0.24
     BitSet
    -0.24
    LookAndFeel
    -0.23
     script
    -0.23
    lah
    -0.23
    POSITIVE LOGITS
    Pipe
    0.30
    è¯ķ
    0.27
     sleep
    0.26
     pipes
    0.26
     pipe
    0.26
     Pipe
    0.25
    åİĭåĬĽ
    0.25
    管éģĵ
    0.24
    ä¸Ń央
    0.24
     Pipes
    0.24
    Activations Density 0.007%

    No Known Activations