© 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. 63555
    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
    对该
    -0.29
     mer
    -0.27
    该
    -0.27
    å¤Ļ
    -0.26
    强
    -0.26
     Tar
    -0.26
    çļĤ
    -0.26
    èķī
    -0.25
    çĶĺ
    -0.25
    è¾¹
    -0.25
    POSITIVE LOGITS
    udios
    0.27
    IVES
    0.26
     Recommend
    0.26
    zM
    0.26
    ervers
    0.26
     def
    0.26
    aptor
    0.26
    GF
    0.26
    _customize
    0.25
    ature
    0.25
    Activations Density 3.886%

    No Known Activations

    This feature has no known activations.