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. 53849
    Prev
    Next
    INDEX
    Explanations

    university

    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
    å¤§éĽ¨
    -0.25
     Geneva
    -0.24
     seal
    -0.24
     seals
    -0.24
    æ°ijå¿ĥ
    -0.24
    æĭ¦æĪª
    -0.23
    FFE
    -0.23
    mai
    -0.23
    fort
    -0.23
    anded
    -0.23
    POSITIVE LOGITS
    eroon
    0.29
    scriptions
    0.27
    缴
    0.26
    atical
    0.25
    _tpl
    0.25
    -fr
    0.24
    模å¼ı
    0.24
    Sizer
    0.24
     act
    0.23
    étr
    0.23
    Activations Density 0.030%

    No Known Activations