© 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. 106914
    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
    Negative Logits
    plement
    -0.28
     dors
    -0.26
     abre
    -0.25
    swer
    -0.25
     ignition
    -0.23
    UNITY
    -0.23
     inade
    -0.23
    rather
    -0.23
    çĶŁäºİ
    -0.23
    å¼ĢéŨ
    -0.23
    POSITIVE LOGITS
    好å¤Ħ
    0.28
    主任
    0.27
    åħļåĴĮ
    0.27
    æģ©
    0.26
     downs
    0.26
    DDS
    0.26
     Herman
    0.25
     scenario
    0.24
     thanks
    0.24
    /Sh
    0.24
    Activations Density 1.110%

    No Known Activations

    This feature has no known activations.