© 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. 130054
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ²½
    -0.28
    tu
    -0.27
    ites
    -0.27
    è´±
    -0.27
    èģĶç½ij
    -0.26
    rite
    -0.26
    FTER
    -0.25
    .JTable
    -0.25
    بÙĬØ©
    -0.25
    åı¥
    -0.24
    POSITIVE LOGITS
    åĤĴ
    0.27
    ç¬ijç¬ij
    0.26
     Transformers
    0.26
    ähr
    0.25
    èĥ½å¤Łè®©
    0.25
    romium
    0.24
     smokers
    0.24
     offenders
    0.23
     scaleFactor
    0.23
    Isl
    0.23
    Activations Density 5.235%

    No Known Activations

    This feature has no known activations.