© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130505
    Prev
    Next
    INDEX
    Explanations

    Boilerplate text

    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
    aty
    -0.31
     wik
    -0.27
    utura
    -0.25
    asti
    -0.25
    orno
    -0.25
     AlertDialog
    -0.25
    athing
    -0.25
     orientation
    -0.24
     brides
    -0.24
     lime
    -0.24
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.61
    å°½éĩı
    0.48
    å¦Ĥæŀľæľī
    0.35
    å°½åĬĽ
    0.34
     spare
    0.32
     whenever
    0.31
    åĦĺ
    0.30
    å°½
    0.30
     opportunity
    0.30
    çĽ¡
    0.30
    Activations Density 53.089%

    No Known Activations