© 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. 62937
    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
    Not in Any Lists

    No Comments

    Negative Logits
    arium
    -0.31
    haft
    -0.30
    eon
    -0.28
    ipl
    -0.26
     cin
    -0.25
    åºĶä»ĺ
    -0.25
     likes
    -0.25
     shares
    -0.25
    inho
    -0.24
    likes
    -0.24
    POSITIVE LOGITS
     ._
    0.34
    çī¹æ®ĬæĥħåĨµ
    0.27
    ç®±
    0.25
    enta
    0.24
    heet
    0.24
     Sheet
    0.24
     auditing
    0.23
    CNT
    0.23
    åŁŃ
    0.23
     cliffs
    0.23
    Activations Density 6.312%

    No Known Activations

    This feature has no known activations.