© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7970
    Prev
    Next
    INDEX
    Explanations

    venture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITTER
    -0.28
    cai
    -0.27
    å·¥ç¨ĭè´¨éĩı
    -0.27
    åģ·
    -0.26
    渲
    -0.25
    梦å¢ĥ
    -0.25
    å°º
    -0.24
    宸
    -0.24
    åĪĨæľŁ
    -0.24
    ä¸ĩ象
    -0.24
    POSITIVE LOGITS
    éĩį
    0.29
    -indent
    0.27
    ohl
    0.27
    ç»
    0.26
    burger
    0.26
    åł¡
    0.26
    伯
    0.25
    é¹°
    0.25
    åѵåĮĸ
    0.25
     invested
    0.24
    Activations Density 0.789%

    No Known Activations