© 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. 95103
    Prev
    Next
    INDEX
    Explanations

    car brands

    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
    LLU
    -0.32
     Hond
    -0.29
    hy
    -0.26
     forbidden
    -0.26
    Ú¾
    -0.26
     flat
    -0.26
    ures
    -0.26
    æİĴ
    -0.25
     dise
    -0.25
    HE
    -0.25
    POSITIVE LOGITS
    管å±Ģ
    0.30
     sor
    0.29
    ä¸Ģ声
    0.28
    ROP
    0.28
    模åŀĭ
    0.26
    çļĦæĶ¿æ²»
    0.26
    getModel
    0.26
     Modelo
    0.25
    æIJħæĭĮ
    0.25
    ARAM
    0.24
    Activations Density 0.022%

    No Known Activations