© 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. 129469
    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
     reversed
    -0.27
     changes
    -0.25
    éĻ£
    -0.25
     Charl
    -0.25
     contrad
    -0.24
    Changed
    -0.24
     Bounty
    -0.24
     opposite
    -0.24
    .eu
    -0.24
    borg
    -0.24
    POSITIVE LOGITS
    esser
    0.28
    mesh
    0.27
    ä½ĵåĨħ
    0.27
    款
    0.27
     Winter
    0.26
    ä»ĸæĽ¾
    0.26
    带ä¸Ĭ
    0.26
    æľīä¸Ģç§į
    0.25
    å½ĵå¹´
    0.24
    èĨ³
    0.24
    Activations Density 31.603%

    No Known Activations

    This feature has no known activations.