© 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. 140853
    Prev
    Next
    INDEX
    Explanations

    central

    np_max-act · gemini-2.0-flash
    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
     ENTER
    -0.27
    èĢIJ
    -0.26
     Wash
    -0.26
    å¦Ĥä½ķçľĭå¾ħ
    -0.25
    ITE
    -0.25
     generously
    -0.25
    _Entry
    -0.24
    åħ·ä½ĵåĨħ容
    -0.24
    DEM
    -0.23
    dex
    -0.23
    POSITIVE LOGITS
    çĽ
    0.28
     câ
    0.26
     CURLOPT
    0.25
    ulet
    0.25
    åī¯ä¼ļéķ¿
    0.25
     agreement
    0.24
    ively
    0.24
    uso
    0.24
    许åı¯è¯ģ
    0.24
    istle
    0.23
    Activations Density 8.074%

    No Known Activations