© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56342
    Prev
    Next
    INDEX
    Explanations

    valuable

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    主è¦ģ
    -0.28
     nah
    -0.26
    athers
    -0.26
    ãģŁ
    -0.25
     souha
    -0.24
    phalt
    -0.24
    æĹ¨åľ¨
    -0.24
     blessed
    -0.24
    @[
    -0.24
     preferable
    -0.24
    POSITIVE LOGITS
    çļĦä¸ľè¥¿
    0.28
     suggestions
    0.27
     resources
    0.27
     subsets
    0.27
    uten
    0.26
    ä¸Ģ件äºĭæĥħ
    0.26
     confusion
    0.25
     combinations
    0.25
    缣
    0.25
     tools
    0.25
    Activations Density 0.041%

    No Known Activations