© 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. 112195
    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
     ster
    -0.26
    èĢĮåĩº
    -0.25
    uten
    -0.24
    èµŀåĬ©
    -0.22
    astery
    -0.22
    ***↵
    -0.22
    kul
    -0.22
     licensed
    -0.22
     sil
    -0.22
     Gund
    -0.22
    POSITIVE LOGITS
    arms
    0.27
    bounds
    0.24
    FetchRequest
    0.24
    æŶåĢĻ
    0.24
     Cheat
    0.24
    á¹ģ
    0.23
    å·¥å§Ķ
    0.23
    è¿Ļä¹Ī大
    0.23
    çļĦåĬ¨ä½ľ
    0.23
    á¹ĥ
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.