© 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. 12-TRANSCODER-HP
    7. 23324
    Prev
    Next
    INDEX
    Explanations

    World War 2 era

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    让大家
    -0.28
    为大家
    -0.27
     Dek
    -0.27
    DDL
    -0.26
    Round
    -0.25
    .ma
    -0.25
    ctors
    -0.24
    ç»Ļ大家
    -0.24
    æĶ¾åѦ
    -0.24
    è¯ĦåĪĨ
    -0.23
    POSITIVE LOGITS
    ç·£
    0.26
    à¤ł
    0.25
    Intern
    0.25
    _handles
    0.25
     Initialized
    0.25
    注åħ¥
    0.24
    ãĤıãģļ
    0.24
    enko
    0.24
    IVERS
    0.24
    à¦Ľ
    0.24
    Activations Density 0.003%

    No Known Activations