© 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. 24-TRANSCODER-HP
    7. 149914
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJij社ä¼ļ
    -0.30
    beck
    -0.26
    sid
    -0.26
    æĽĻ
    -0.25
     sidel
    -0.25
    æݢ访
    -0.25
    habi
    -0.24
    ensch
    -0.24
    åĸĦ
    -0.24
    dzi
    -0.24
    POSITIVE LOGITS
     Interr
    0.25
    дов
    0.24
     Toro
    0.24
     Vand
    0.24
    strt
    0.24
     Romans
    0.24
     Supporting
    0.24
    iect
    0.23
    valid
    0.23
     tủ
    0.23
    Activations Density 1.326%

    No Known Activations