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. 53862
    Prev
    Next
    INDEX
    Explanations

    dates and legal/academic contexts

    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
    ä¾Ľç͵
    -0.27
    isol
    -0.26
    ]+$
    -0.26
     disb
    -0.25
     soft
    -0.25
    Ø´Ùĩ
    -0.24
    软
    -0.24
    olated
    -0.24
    âķ°
    -0.24
     Soft
    -0.24
    POSITIVE LOGITS
    ventions
    0.25
     Wine
    0.25
     trustee
    0.25
    æĪĺèĥľ
    0.25
    è¿İ
    0.24
     Thank
    0.24
    å¾ĹçĽĬ
    0.24
    ussen
    0.24
     wash
    0.24
    ucer
    0.23
    Activations Density 0.005%

    No Known Activations