© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 271
    Prev
    Next
    INDEX
    Explanations

    aic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ»ŀåIJİ
    -0.25
    iram
    -0.25
    drs
    -0.24
    .isChecked
    -0.24
    -Cs
    -0.24
    .checked
    -0.23
    æİĪ
    -0.23
    æĬĹæĭĴ
    -0.23
    ogh
    -0.23
    rapped
    -0.23
    POSITIVE LOGITS
    бл
    0.30
    ä¸įä¿¡
    0.29
    칫
    0.28
    驱
    0.28
    èħĶ
    0.25
    -speed
    0.25
    鼷
    0.25
    彦
    0.25
    alo
    0.24
    anth
    0.24
    Activations Density 0.020%

    No Known Activations