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. 1716
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    å͝æľī
    -0.28
    flu
    -0.27
    оÑĩнÑĭÑħ
    -0.26
    åIJ«éĩı
    -0.26
    ertz
    -0.25
    å͝
    -0.25
    ERT
    -0.25
    anches
    -0.24
    brew
    -0.24
     ì¶
    -0.23
    POSITIVE LOGITS
    ä¸Ģ个å¤ļ
    0.31
    indle
    0.25
     learned
    0.25
     Patel
    0.25
    åŃij
    0.25
     Stake
    0.24
     Assertion
    0.24
    astery
    0.24
    acic
    0.24
    .learning
    0.23
    Activations Density 0.006%

    No Known Activations