© 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. 112663
    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
     convince
    -0.31
    满æĦıçļĦ
    -0.28
    å½ĵä¹ĭ
    -0.27
    ä»ĸ认为
    -0.26
    "profile
    -0.25
    æĪ¾
    -0.24
    )').
    -0.24
     bound
    -0.24
    ä¼ļåIJĮ
    -0.24
    Propagation
    -0.23
    POSITIVE LOGITS
    ulous
    0.30
    ÑĦикÑģ
    0.26
    erp
    0.26
    ORITY
    0.25
    è¶Ĭ好
    0.25
    uel
    0.24
    iris
    0.23
    ìľĦ
    0.23
    æ°ijçĶŁ
    0.23
     mirrors
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.