© 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. 129506
    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
     clear
    -0.31
     dens
    -0.27
     confl
    -0.27
    çļĦ好
    -0.26
     localized
    -0.26
    incinn
    -0.25
    æľĹ
    -0.25
    åīĶ
    -0.25
     confuse
    -0.25
     actively
    -0.24
    POSITIVE LOGITS
    åĨµ
    0.27
    調
    0.26
    éŀħ
    0.25
    è°ĥ解
    0.25
     africa
    0.25
    wright
    0.24
     friday
    0.24
    æ³ģ
    0.24
    代表
    0.24
    marks
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.