© 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. 20-TRANSCODER-HP
    7. 128991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ²ĵ
    -0.29
    ieder
    -0.28
    itore
    -0.28
    èĢĮåİ»
    -0.27
     libs
    -0.26
    注æĺİåĩºå¤Ħ
    -0.25
    urance
    -0.25
    иÑĢÑĥÑİÑĤ
    -0.24
    noop
    -0.24
    æĸ¥
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĪĻ
    0.30
    rts
    0.28
    éĽĩ
    0.28
    ()][
    0.25
     cref
    0.25
     mascul
    0.24
    ebra
    0.24
    appoint
    0.23
    俸
    0.23
    诡
    0.23
    Activations Density 24.648%

    No Known Activations

    This feature has no known activations.