© 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. 35-TRANSCODER-HP
    7. 40768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĺĶ
    -0.26
    ç´¢
    -0.26
    转
    -0.26
    rename
    -0.25
    å«ļ
    -0.24
    PropertyDescriptor
    -0.24
    Injector
    -0.24
    shi
    -0.23
    IGIN
    -0.23
     fread
    -0.23
    POSITIVE LOGITS
    STER
    0.29
    æŀľ
    0.27
    ói
    0.26
    oste
    0.26
    IMO
    0.25
    úc
    0.25
    ç®ĹäºĨ
    0.24
    bolt
    0.24
    tero
    0.24
    CTYPE
    0.24
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.