© 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. 112067
    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
    è¯Ŀ
    -0.27
    è¯Ŀ说
    -0.27
    è¾¹ç¼ĺ
    -0.26
    immel
    -0.26
    è¿ĩå¾Ģ
    -0.24
    exo
    -0.24
    æķ´ä½ĵ
    -0.24
    çİ°è¡Į
    -0.24
    Overall
    -0.23
    ä¸įæİĴéĻ¤
    -0.23
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵
    0.24
    ptime
    0.24
    _party
    0.23
    æı®
    0.23
    seed
    0.23
    pics
    0.23
    lift
    0.23
     representative
    0.23
    /mainwindow
    0.23
     Kurds
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.