© 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. 112748
    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
    interfaces
    -0.27
     PET
    -0.26
    PET
    -0.26
    ä¸Ģä¸ĭ
    -0.25
    ify
    -0.25
     Pett
    -0.25
     palms
    -0.24
    iface
    -0.23
     averages
    -0.23
     cams
    -0.23
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.25
    .googlecode
    0.24
    aub
    0.23
    继æī¿
    0.23
    .GetAsync
    0.23
    ted
    0.23
    å²±
    0.23
    éļ¶å±ŀ
    0.23
    å±Ĭæ¯ķä¸ļçĶŁ
    0.23
    ä¿¡æģ¯åıijå¸ĥ
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.