© 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. 96056
    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
    ç½®
    -0.26
    å¢Ł
    -0.24
    slider
    -0.24
    >Show
    -0.24
    ivec
    -0.24
     OnPropertyChanged
    -0.24
    erness
    -0.24
     slider
    -0.24
    rule
    -0.24
     Nielsen
    -0.24
    POSITIVE LOGITS
    ħ§
    0.30
     Skull
    0.29
    éĢļè¿ĩ对
    0.27
    ç©¿éĢı
    0.27
    bear
    0.25
    ompiler
    0.25
    æ°¸ä¹ħ
    0.25
    etAddress
    0.25
    å¿ĹæĦ¿
    0.25
    ett
    0.24
    Activations Density 0.885%

    No Known Activations

    This feature has no known activations.