© 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. 96628
    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
    é«ĵ
    -0.27
    emons
    -0.27
    å¤ļ
    -0.26
    èĥ½èĢĹ
    -0.25
    emo
    -0.24
    ìħĢ
    -0.24
    æĪĸå¤ļ
    -0.23
    cloud
    -0.23
    åħļæĶ¿
    -0.23
     EXPRESS
    -0.23
    POSITIVE LOGITS
    åĺĺ
    0.28
     Barker
    0.26
     punctuation
    0.26
     unp
    0.26
    -shadow
    0.25
     purpos
    0.25
    ªĮ
    0.25
     ever
    0.24
     measures
    0.24
     Liberty
    0.24
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.