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. 0-TRANSCODER-HP
    4. 20
    Prev
    Next
    INDEX
    Explanations

    Jun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _supp
    -0.29
    åĽ½ç±į
    -0.28
     (_,
    -0.27
    isRequired
    -0.25
    _EOL
    -0.24
    &amp
    -0.24
    uis
    -0.24
    lags
    -0.24
    itere
    -0.23
    uter
    -0.23
    POSITIVE LOGITS
    asin
    0.27
    arLayout
    0.26
    次
    0.24
    å±Ģ
    0.24
    Invoker
    0.23
    éĴĪ
    0.22
    itos
    0.22
    laps
    0.22
     Comput
    0.22
    å¨ĺå¨ĺ
    0.22
    Activations Density 6.937%

    No Known Activations