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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58180
    Prev
    Next
    INDEX
    Explanations

    Technology and adoption

    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
    æł¼å¤ĸ
    -0.28
     Whites
    -0.27
    /html
    -0.25
     zro
    -0.25
    ÂŃs
    -0.24
    å¢ĺ
    -0.24
    ç½ijç«Ļé¦ĸ页
    -0.24
    ignant
    -0.24
    ENDER
    -0.24
    éĢĤ
    -0.24
    POSITIVE LOGITS
     Ever
    0.28
     ever
    0.26
    uida
    0.25
     Challenge
    0.25
    .Scale
    0.25
    MAS
    0.24
    cluded
    0.24
     them
    0.24
    MEM
    0.24
    .managed
    0.24
    Activations Density 0.004%

    No Known Activations