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. 125811
    Prev
    Next
    INDEX
    Explanations

    the

    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
    æĿĤ
    -0.33
    sam
    -0.29
    echa
    -0.28
    鼾
    -0.27
    efa
    -0.25
    gies
    -0.24
     jul
    -0.24
    éĥ½è®¤ä¸º
    -0.24
    ä½łè§īå¾Ĺ
    -0.23
     enforcing
    -0.23
    POSITIVE LOGITS
    æĮĩæłĩ
    0.27
    ssue
    0.25
     tentative
    0.25
    大大å°ı
    0.25
    tent
    0.24
     circ
    0.24
    ER
    0.24
    SSF
    0.23
     bounded
    0.23
     indicator
    0.23
    Activations Density 0.069%

    No Known Activations