© 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. 112435
    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
    isms
    -0.29
     subst
    -0.25
    erek
    -0.23
    æĬĵ
    -0.23
    æĸ¹éĿ¢
    -0.23
    çĶ¨åĵģ
    -0.23
     Tas
    -0.23
     акÑĤив
    -0.23
    ikip
    -0.22
    åħ³äºİæĪij们
    -0.22
    POSITIVE LOGITS
    itational
    0.25
    undra
    0.24
     BaseController
    0.24
    yal
    0.24
    emode
    0.23
    ä¸Ģå¹´ä¸Ģ度
    0.23
    .hostname
    0.23
     csr
    0.23
     background
    0.23
    çIJħ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.