© 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. 64670
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    Negative Logits
    ends
    -0.28
    presso
    -0.28
    .nr
    -0.26
    æ´Ĺå¹²åĩĢ
    -0.26
    ĽĦ
    -0.25
    åıĹ
    -0.25
     DISCLAIM
    -0.25
    åıĹåĪ°
    -0.25
    quist
    -0.25
     bearings
    -0.24
    POSITIVE LOGITS
    大åѦ
    0.29
    uParam
    0.28
    è¯ī
    0.26
    suma
    0.26
    iten
    0.25
    大åѸ
    0.25
    acam
    0.24
    etCode
    0.24
     hel
    0.24
    bilt
    0.24
    Activations Density 56.123%

    No Known Activations