© 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. 95433
    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
     themselves
    -0.29
     tá»ı
    -0.28
     oneself
    -0.27
    itical
    -0.26
    çĸĹ
    -0.26
    eos
    -0.26
     herself
    -0.25
    æĦĪ
    -0.24
     yourself
    -0.24
     Gone
    -0.24
    POSITIVE LOGITS
     outputPath
    0.28
    _hdl
    0.27
    æľŁåĨħ
    0.27
     handwriting
    0.27
    ony
    0.26
    -ins
    0.25
    mons
    0.25
    表éĿ¢ä¸Ĭ
    0.25
    starttime
    0.24
    山谷
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.