© 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. 30-TRANSCODER-HP
    7. 96887
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    furt
    -0.28
    eve
    -0.28
    åĪĴ
    -0.27
    ationToken
    -0.26
    hift
    -0.26
    erv
    -0.26
    LinkId
    -0.25
    æ·¡
    -0.25
    å°ij
    -0.25
    vang
    -0.24
    POSITIVE LOGITS
    ä¼ģä¸ļ管çIJĨ
    0.30
    HAM
    0.28
    声åĵį
    0.27
    моÑĢ
    0.27
    ams
    0.27
    书ä¸Ń
    0.26
     yourselves
    0.26
     Wizards
    0.25
    被æīĵ
    0.24
    é¤ĺ
    0.24
    Activations Density 0.886%

    No Known Activations