© 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. 130134
    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
    å¤Ħæĸ¹
    -0.27
     Epid
    -0.27
     epid
    -0.26
    ep
    -0.26
    XP
    -0.24
     Ñģебе
    -0.24
     slik
    -0.24
    nameof
    -0.23
    人群
    -0.23
    è£Ļ
    -0.23
    POSITIVE LOGITS
    idia
    0.25
    ìĹĶ
    0.25
    yles
    0.25
    -opacity
    0.25
    æľī幸
    0.25
    enerated
    0.24
     appeal
    0.24
    uetype
    0.24
    .getLength
    0.24
     LogManager
    0.23
    Activations Density 3.160%

    No Known Activations

    This feature has no known activations.