© 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. 96686
    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
     Quick
    -0.28
    éªĬ
    -0.26
     forge
    -0.24
     Rim
    -0.24
    inating
    -0.23
    çĨ¹
    -0.23
    é¢Ħæ¡Ī
    -0.23
    ä¼¼
    -0.23
     Boh
    -0.23
    ,:
    -0.23
    POSITIVE LOGITS
     thing
    0.28
    ardin
    0.25
    (thing
    0.25
    _SEP
    0.25
    .resume
    0.25
    woord
    0.25
    persist
    0.25
    _resume
    0.24
    exchange
    0.24
    rbrakk
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.