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. 7-TRANSCODER-HP
    4. 24118
    Prev
    Next
    INDEX
    Explanations

    pt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouri
    -0.32
    çŃĶé¢ĺ
    -0.26
    va
    -0.26
    tür
    -0.25
    é©·
    -0.25
    adera
    -0.25
    {name
    -0.24
    åĨħç½®
    -0.24
    ãĥĻãĤ¹ãĥĪ
    -0.24
     contest
    -0.23
    POSITIVE LOGITS
    CEPTION
    0.27
    weit
    0.25
    ernel
    0.25
     Nas
    0.24
    æµģä¼ł
    0.23
    emp
    0.23
     Polit
    0.23
    iek
    0.23
    马ä¸Ĭ
    0.23
    جÙĨ
    0.23
    Activations Density 0.781%

    No Known Activations