© 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. 140562
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    çĮĽçĦ¶
    -0.26
     flour
    -0.26
    yr
    -0.25
    åł¤
    -0.25
    -shell
    -0.24
    .hibernate
    -0.24
    æĬĺ
    -0.24
    åĶij
    -0.23
     Pride
    -0.23
     fl
    -0.23
    POSITIVE LOGITS
    ulen
    0.29
    åı¯çĶ¨äºİ
    0.28
    çİĩè¾¾
    0.27
    /Instruction
    0.26
    ungs
    0.26
    åĩºå·®
    0.25
    çİĩè¾¾åĪ°
    0.25
    ensburg
    0.25
    obuf
    0.25
    Ĥæķ°
    0.24
    Activations Density 21.620%

    No Known Activations