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. 53867
    Prev
    Next
    INDEX
    Explanations

    filler words and punctuation

    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
    endency
    -0.26
     rejection
    -0.26
    anness
    -0.25
    "..
    -0.25
    ornings
    -0.25
    inos
    -0.24
    _printf
    -0.24
    ðŁijİ
    -0.24
    æĭĴ
    -0.24
     forest
    -0.24
    POSITIVE LOGITS
    路人
    0.28
    isci
    0.27
     correctly
    0.27
    亶
    0.26
    å¼ĢåıijèĢħ
    0.26
    éĩijéĴ±
    0.25
    å¿Ĺ
    0.25
    åķĨçĶ¨è½¦
    0.24
     hamm
    0.24
    æĥķ
    0.24
    Activations Density 0.133%

    No Known Activations