© 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. 22-TRANSCODER-HP
    7. 98883
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ¤æ¬¡
    -0.29
    è¿Ļ次
    -0.29
     anew
    -0.27
    åѦä½į
    -0.27
    è¿Ļä¸Ģ次
    -0.25
     workflow
    -0.24
    baugh
    -0.24
    strate
    -0.23
    /trunk
    -0.23
    entry
    -0.23
    POSITIVE LOGITS
     Bund
    0.28
    zelf
    0.28
    åŃ°
    0.27
    isel
    0.26
    isse
    0.25
    ADM
    0.25
    ucks
    0.25
    ctors
    0.24
     fram
    0.24
     unp
    0.24
    Activations Density 0.015%

    No Known Activations