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. 46525
    Prev
    Next
    INDEX
    Explanations

    all

    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
    -peer
    -0.26
    ãĥĹãĥ¬ãĤ¼
    -0.26
    ť
    -0.24
    oulos
    -0.24
    .cleanup
    -0.24
    exampleInput
    -0.23
    罩
    -0.23
     scouting
    -0.23
    .performance
    -0.23
    óng
    -0.23
    POSITIVE LOGITS
    avic
    0.29
    好çľĭ
    0.28
    jp
    0.28
    angkan
    0.26
    obj
    0.26
    enko
    0.24
    对象
    0.24
    è¶ħé«ĺ
    0.24
    çĩ¥
    0.24
    andre
    0.24
    Activations Density 0.013%

    No Known Activations