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. 328
    Prev
    Next
    INDEX
    Explanations

    ring

    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
     Rach
    -0.27
    æĽ³
    -0.25
    -fr
    -0.25
    ä¸įè§£
    -0.25
     doubtful
    -0.24
    ä»ħ为
    -0.24
    amment
    -0.24
    enas
    -0.23
    -clean
    -0.23
    å°ij
    -0.23
    POSITIVE LOGITS
    lek
    0.26
    å·¥
    0.26
    otron
    0.26
    mez
    0.26
    ulk
    0.25
    istik
    0.25
    å®´
    0.25
    té
    0.25
    OV
    0.24
     trays
    0.24
    Activations Density 0.002%

    No Known Activations