© 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. 8709
    Prev
    Next
    INDEX
    Explanations

    logos

    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
    å¤
    -0.27
    æĬĹçĻĮ
    -0.25
    ç³ĸå°¿çĹħ
    -0.23
    çīµ
    -0.23
    EditingController
    -0.23
    æĪĬ
    -0.23
     insulin
    -0.23
    ãģ£ãģ¡
    -0.23
     nghiá»ĩp
    -0.23
     onActivityResult
    -0.23
    POSITIVE LOGITS
     logo
    0.71
     logos
    0.66
    é¢ľèī²
    0.62
    logo
    0.60
     colors
    0.60
     icon
    0.60
    åĽ¾æłĩ
    0.59
     color
    0.57
    Logo
    0.56
     Logo
    0.56
    Activations Density 0.001%

    No Known Activations