© 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. 96075
    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
    alendar
    -0.28
    али
    -0.28
    åĵŁ
    -0.26
    elic
    -0.25
    istical
    -0.25
    æīĢè°ĵ
    -0.24
    åŁºç¡Ģ设æĸ½
    -0.24
    odes
    -0.24
    inger
    -0.24
    oom
    -0.23
    POSITIVE LOGITS
    tright
    0.26
    rait
    0.25
    MT
    0.24
    æ´¨
    0.24
    amide
    0.24
    acre
    0.23
     deed
    0.23
    unken
    0.23
    leon
    0.23
    ç¾İçļĦ
    0.23
    Activations Density 0.100%

    No Known Activations

    This feature has no known activations.