© 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. 111788
    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
    ä¼ŀ
    -0.28
     Barr
    -0.26
     Borough
    -0.26
    locks
    -0.26
    çī¹
    -0.25
    è´¯
    -0.24
    heim
    -0.23
    iminal
    -0.23
    æĭ¯
    -0.23
    ledge
    -0.23
    POSITIVE LOGITS
     issuance
    0.27
    å«Įçĸij
    0.24
    lie
    0.24
     arguing
    0.24
    å¾Ĺèµ·
    0.24
    éħĹ
    0.24
    æĦıæĢĿæĺ¯
    0.23
    .findViewById
    0.23
    entifier
    0.23
    CustomerId
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.