© 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. 77
    Prev
    Next
    INDEX
    Explanations

    burn

    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
    hus
    -0.30
    eight
    -0.28
    EDGE
    -0.25
    æĹ©çĤ¹
    -0.24
    isme
    -0.24
    edge
    -0.23
    梯éĺŁ
    -0.23
    ãģ¦ãģĬãģı
    -0.23
     EDGE
    -0.23
    WRITE
    -0.23
    POSITIVE LOGITS
    afil
    0.27
    éĹª
    0.25
    åģļ
    0.25
    车
    0.24
     chÃŃ
    0.24
    érc
    0.24
    /she
    0.24
    éĹ¾
    0.23
    ç«Ļåľ¨
    0.23
    çķħ
    0.23
    Activations Density 0.021%

    No Known Activations