© 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. 12-TRANSCODER-HP
    7. 22933
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /terms
    -0.27
    æķ¬ä¸ļ
    -0.26
    è¯ģæį®
    -0.26
    æĶ¯æŁ±
    -0.26
    "],↵
    -0.25
    è®°å¾Ĺ
    -0.25
    ých
    -0.25
    Truth
    -0.24
    èĢĨ
    -0.24
    .rawValue
    -0.24
    POSITIVE LOGITS
    ToOne
    0.29
     SOFTWARE
    0.28
     Zah
    0.27
     NU
    0.27
     PAN
    0.27
    pag
    0.27
    éal
    0.27
    æ±Ŀ
    0.26
     Heaven
    0.26
    Pag
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.