© 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. 142757
    Prev
    Next
    INDEX
    Explanations

    Chemical formulas and data

    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
    ARTH
    -0.27
    estone
    -0.27
    umper
    -0.26
    è²Į
    -0.25
    _ping
    -0.25
    QRSTUV
    -0.24
    ianne
    -0.24
    emons
    -0.24
    è¨Ģ论
    -0.24
    unde
    -0.23
    POSITIVE LOGITS
     tit
    0.30
    داÙħ
    0.26
    满
    0.26
    Ю
    0.26
    åĨħç§ij
    0.26
    éĢĤ
    0.26
    eria
    0.26
     detail
    0.25
     chance
    0.25
    çİij
    0.25
    Activations Density 3.042%

    No Known Activations