© 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. 9862
    Prev
    Next
    INDEX
    Explanations

    album

    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
     refunds
    -0.26
    åݻ买
    -0.25
     refreshing
    -0.25
     refresh
    -0.25
    _formats
    -0.25
    ä¸ĢåįĬ
    -0.25
    åĪ·æĸ°
    -0.25
    ä¸Ģä¼ļåĦ¿
    -0.24
    åħħ
    -0.24
    çĶŁäº§çļĦ
    -0.24
    POSITIVE LOGITS
    umer
    0.31
    缮çļĦ
    0.28
    REEN
    0.28
    åī¯
    0.27
    ropriate
    0.27
    ponent
    0.26
    ym
    0.24
    #End
    0.24
    tractor
    0.24
    stre
    0.24
    Activations Density 0.006%

    No Known Activations