© 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. 27-TRANSCODER-HP
    7. 56572
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .initState
    -0.30
    	when
    -0.28
     when
    -0.27
    Began
    -0.26
    å½ĵä»ĸ
    -0.26
    }*
    -0.26
     When
    -0.25
    ajs
    -0.25
    onium
    -0.24
    æĿĤ
    -0.24
    POSITIVE LOGITS
    åħ³æ³¨åº¦
    0.27
     favored
    0.26
    favor
    0.26
    plevel
    0.24
    æľĢæľī
    0.24
    æħİ
    0.24
     sweep
    0.24
    æŃ£åĢ¼
    0.24
     preferred
    0.24
    изаÑĤоÑĢ
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.