© 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. 27-TRANSCODER-HP
    7. 56320
    Prev
    Next
    INDEX
    Explanations

    coding "use" command

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĥ½æī¾åĪ°
    -0.31
    æī¾åĪ°äºĨ
    -0.30
    èĥ½åľ¨
    -0.30
    atical
    -0.27
    åıijçİ°èĩªå·±
    -0.25
    æľīæľºä¼ļ
    -0.25
    æ¸
    -0.24
    Scoped
    -0.24
    æī¾åĪ°
    -0.24
    éļ¾åħį
    -0.24
    POSITIVE LOGITS
     use
    0.49
     show
    0.44
    use
    0.43
    _use
    0.40
     include
    0.39
    Use
    0.39
     Use
    0.38
     force
    0.37
     treat
    0.37
    USE
    0.36
    Activations Density 0.031%

    No Known Activations