© 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. 95957
    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
    ourt
    -0.28
     kön
    -0.27
    å¼¹
    -0.26
    ices
    -0.25
    ibly
    -0.25
    åħ¨èĥ½
    -0.25
    åį³æŶ
    -0.24
     PHYS
    -0.24
    æŀľæ±ģ
    -0.24
    iev
    -0.23
    POSITIVE LOGITS
    ewe
    0.30
    heim
    0.27
     hemisphere
    0.27
     pimp
    0.25
    两ä¼ļ
    0.25
    å°ıå¾®
    0.25
     dwar
    0.24
    emento
    0.24
    cool
    0.24
    enso
    0.24
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.