© 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. 27-TRANSCODER-HP
    7. 57354
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulp
    -0.27
     complexity
    -0.26
    ut
    -0.25
     wraps
    -0.25
    表示
    -0.24
    åĤ¨éĩı
    -0.24
     hom
    -0.24
     solving
    -0.24
    æĮģ
    -0.23
    å®ŀè¡Į
    -0.23
    POSITIVE LOGITS
    çĸµ
    0.29
    çķ´
    0.28
    åĨįå¤ļ
    0.27
    çĶŁæ´»ä¹łæĥ¯
    0.24
    è¦ģä¸įè¦ģ
    0.24
    æĻ¯è§Ĥ
    0.24
     Denmark
    0.23
    ENE
    0.23
    ä¸ºä½ł
    0.23
    OrderId
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.