© 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. 87832
    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
     intr
    -0.31
     too
    -0.28
    åķĨåĬ¡
    -0.27
    ä¿®
    -0.27
    ert
    -0.27
    æıĴ
    -0.26
     commercial
    -0.26
    ergy
    -0.26
     involved
    -0.26
     close
    -0.26
    POSITIVE LOGITS
    LoginForm
    0.27
    acre
    0.26
    물ìĿĦ
    0.26
    åħ¨æł¡
    0.25
    çĪ±äºº
    0.25
    facebook
    0.24
    OLD
    0.24
    MSN
    0.24
    LLU
    0.24
    /OR
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.