© 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. 107280
    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
     ke
    -0.28
    è·¯
    -0.27
    onom
    -0.27
    ä¸įæĪIJ
    -0.26
    çĻ»
    -0.25
    ")]↵
    -0.25
    Collapsed
    -0.24
    åı¬å¼Ģ
    -0.24
    ican
    -0.24
    strap
    -0.24
    POSITIVE LOGITS
    .obj
    0.30
    ignet
    0.28
    jq
    0.27
    psc
    0.26
    iterator
    0.25
     Rou
    0.25
    \Collection
    0.24
    [obj
    0.24
    enet
    0.24
    é§IJ
    0.24
    Activations Density 0.072%

    No Known Activations

    This feature has no known activations.