© 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. 96068
    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
     stir
    -0.27
     hÆ°á»Łng
    -0.27
     Kỳ
    -0.25
    ä¸ŃæĸŃ
    -0.25
    scoped
    -0.25
    doch
    -0.24
     buz
    -0.23
    epy
    -0.23
     interrupted
    -0.23
     Medium
    -0.23
    POSITIVE LOGITS
    滥çĶ¨
    0.29
     grown
    0.29
    lein
    0.27
    ugin
    0.27
     zug
    0.26
    ŀĭ
    0.26
     destinations
    0.25
     anthrop
    0.25
    edList
    0.24
    大人
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.