© 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. 95476
    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
    请åıĬæŶ
    -0.26
     aute
    -0.26
    èĮļ
    -0.26
    akter
    -0.26
     American
    -0.26
    æ®
    -0.25
    istant
    -0.25
    еÑĢиал
    -0.24
    çļĦæłĩåĩĨ
    -0.24
    ressed
    -0.24
    POSITIVE LOGITS
     Barb
    0.27
    sburg
    0.26
    _spot
    0.24
    æľĢ好ä¸įè¦ģ
    0.24
    ocking
    0.24
     dafür
    0.24
    .OP
    0.23
    _sound
    0.23
    éĦ±
    0.23
    avor
    0.23
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.