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. 1693
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ieval
    -0.30
    develop
    -0.29
    urance
    -0.26
    tems
    -0.25
    examples
    -0.25
    SI
    -0.24
    Si
    -0.24
    ãģĴ
    -0.24
    GY
    -0.24
    ROY
    -0.24
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸Ĭา
    0.25
    anth
    0.25
     &'
    0.25
    ç©°
    0.24
    两ä¼ļ
    0.24
    -Core
    0.23
    WM
    0.23
    ç²īèī²
    0.23
    -serving
    0.22
    å¦Ĩ
    0.22
    Activations Density 0.000%

    No Known Activations