© 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. 96073
    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
    æ¡ģ
    -0.28
    otype
    -0.27
    ublic
    -0.25
    anvas
    -0.25
    ä½ľèĢħæľ¬äºº
    -0.24
     observes
    -0.24
    æĤ²
    -0.24
    uble
    -0.24
     Matcher
    -0.24
     gap
    -0.24
    POSITIVE LOGITS
    (logging
    0.28
     Enemies
    0.27
    ä¸ĢæĿ¡
    0.27
    stück
    0.26
    stoff
    0.26
    ä¸Ģå¥Ĺ
    0.26
    å¥Ĺ
    0.25
    ltra
    0.24
    nyder
    0.24
    åĿIJ
    0.24
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.