© 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. 30-TRANSCODER-HP
    7. 96644
    Prev
    Next
    INDEX
    Explanations

    group

    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
    Not in Any Lists

    No Comments

    Negative Logits
    dings
    -0.25
    èļĮ
    -0.25
    è¿ŀäºij
    -0.24
    åľ¨çİ°åľº
    -0.23
    establish
    -0.23
     Protector
    -0.23
    enate
    -0.23
     Pirate
    -0.23
    аÑĩ
    -0.23
    é²İ
    -0.23
    POSITIVE LOGITS
     group
    0.93
     groups
    0.86
    group
    0.84
    群
    0.79
     Group
    0.78
    Group
    0.77
     Groups
    0.76
     GROUP
    0.75
    groups
    0.75
    GROUP
    0.75
    Activations Density 0.959%

    No Known Activations