© 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. 98372
    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
    ships
    -0.28
    DataTask
    -0.26
    uki
    -0.26
     pls
    -0.25
    们éĥ½
    -0.24
    hower
    -0.24
     getEmail
    -0.24
    èĦij
    -0.24
     [âĢ¦]
    -0.24
    utes
    -0.23
    POSITIVE LOGITS
    åıĤä¸İåĪ°
    0.27
    æľĪ以æĿ¥
    0.27
    æĸ°ä¸ŃåĽ½
    0.24
     intervening
    0.24
    иÑĢÑĥ
    0.24
    -reset
    0.24
    aron
    0.23
    æİ¥æīĭ
    0.23
     anthrop
    0.23
     spreading
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.