© 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. 30-TRANSCODER-HP
    7. 96706
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renters
    -0.26
    èĻļ
    -0.26
    olor
    -0.26
    诱导
    -0.25
    entes
    -0.25
    åı¯ä»¥æĽ´å¥½
    -0.25
    owment
    -0.24
    å¿Į
    -0.24
    elden
    -0.24
    zers
    -0.24
    POSITIVE LOGITS
     package
    0.27
    æĹ¥çĶµ
    0.25
    eve
    0.25
    odos
    0.24
    亨
    0.23
     slab
    0.23
    pkg
    0.23
     ThemeData
    0.23
    manship
    0.23
     carrier
    0.23
    Activations Density 0.108%

    No Known Activations

    This feature has no known activations.