© 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. 130537
    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
    obl
    -0.25
     “âĢ¦
    -0.25
    ÃŁ
    -0.25
     ken
    -0.24
     finde
    -0.24
    ò
    -0.24
    instead
    -0.24
    伶
    -0.24
    åĪ©çĶ¨çİĩ
    -0.24
    ok
    -0.23
    POSITIVE LOGITS
    ä½ĵ彩
    0.28
    åĮ»åĬ¡
    0.27
    Lens
    0.25
    -translate
    0.25
    çī¹æ´¾
    0.24
    书记
    0.24
    éĥ½è®¤ä¸º
    0.24
    adders
    0.24
    _epi
    0.24
    ä¸įè´Ł
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.