© 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. 57586
    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
    æ¹ĸåĮº
    -0.32
    äºĴè¡¥
    -0.28
    ä¿Ŀ
    -0.28
    aul
    -0.28
    (IO
    -0.26
    %^
    -0.25
    esco
    -0.25
    åĪĽæĸ°èĥ½åĬĽ
    -0.25
    å¾®è§Ĥ
    -0.24
    两个维æĬ¤
    -0.24
    POSITIVE LOGITS
    åħŃåIJĪ
    0.27
    è´»
    0.27
    ĵį
    0.26
    åįıè°ĥ
    0.26
     Tick
    0.26
    Tick
    0.25
    exemple
    0.24
    纡
    0.24
     Berm
    0.24
    ÅĽl
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.