© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96860
    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
    eus
    -0.30
    iped
    -0.28
    éĿĻéĿĻ
    -0.26
    mer
    -0.25
    以èī²
    -0.25
    åIJ¸åıĸ
    -0.25
    ialis
    -0.25
    krit
    -0.25
    .intellij
    -0.24
    éĿĻ
    -0.24
    POSITIVE LOGITS
     CWE
    0.25
    éĻIJåĪ¶
    0.25
     OL
    0.24
     restraining
    0.24
     CPPUNIT
    0.23
    adjust
    0.23
    IGH
    0.23
    getTime
    0.23
     tavern
    0.23
    ete
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.