© 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. 98628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    odia
    -0.29
    æ»Ł
    -0.27
    itta
    -0.27
    ça
    -0.27
    /wiki
    -0.26
    éķ¿å¤§äºĨ
    -0.26
    stration
    -0.25
    IRE
    -0.24
    andy
    -0.24
    ]."
    -0.24
    POSITIVE LOGITS
    份é¢Ŀ
    0.31
    éķij
    0.27
    ä¸Ģç»ı
    0.26
    WithDuration
    0.25
    åħ¬ç«ł
    0.25
    pg
    0.24
    åĽłåħ¶
    0.24
    份
    0.24
    missing
    0.24
    dur
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.