© 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. 94965
    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
    Negative Logits
    Grad
    -0.27
    ç®Ń
    -0.26
     Delay
    -0.26
    delay
    -0.26
     delayed
    -0.26
     Wort
    -0.26
    ledged
    -0.26
    å°Ĩåħ¶
    -0.26
     Grad
    -0.25
    _delay
    -0.25
    POSITIVE LOGITS
    upon
    0.28
    maries
    0.27
    ç»·
    0.27
    tsx
    0.25
    -May
    0.25
    ***↵↵
    0.25
     Manip
    0.25
     ends
    0.24
     majority
    0.24
    fähig
    0.24
    Activations Density 2.077%

    No Known Activations

    This feature has no known activations.