© 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. 25-TRANSCODER-HP
    7. 109241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŀĭä¼ģä¸ļ
    -0.26
    jer
    -0.26
     convo
    -0.25
     closets
    -0.25
    MAL
    -0.25
    fmt
    -0.25
     Administrator
    -0.24
    ứng
    -0.24
    zug
    -0.24
    arsers
    -0.24
    POSITIVE LOGITS
    baugh
    0.28
    èĶļ
    0.26
     verm
    0.25
    otonin
    0.25
    itas
    0.24
    atch
    0.24
    æ´Ĵ
    0.23
    otas
    0.23
    ACHI
    0.23
    ottom
    0.23
    Activations Density 2.462%

    No Known Activations

    This feature has no known activations.