© 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. 20-TRANSCODER-HP
    7. 107910
    Prev
    Next
    INDEX
    Explanations

    House and building parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oS
    -0.28
    宾
    -0.27
    ...↵
    -0.27
    en
    -0.26
    e
    -0.26
    oner
    -0.25
     charset
    -0.24
    kh
    -0.24
    rec
    -0.24
    æ°ij
    -0.24
    POSITIVE LOGITS
    à¸Ńà¸Ńà¸ģà¸Īาà¸ģ
    0.25
     GPA
    0.24
    rese
    0.24
     ÐijÑĢ
    0.24
    findAll
    0.24
    ombat
    0.23
    iaux
    0.23
    akit
    0.23
    ories
    0.23
    phe
    0.23
    Activations Density 8.450%

    No Known Activations