© 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. 9598
    Prev
    Next
    INDEX
    Explanations

    Sentence fragments in narratives

    np_max-act-logits · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     special
    -0.27
    visor
    -0.26
     encounters
    -0.26
     remin
    -0.26
     especial
    -0.26
    -special
    -0.25
     scraper
    -0.25
    åIJĥè¿ĩ
    -0.25
    special
    -0.25
    ä¾ĭå¤ĸ
    -0.25
    POSITIVE LOGITS
    æĹ¢æľī
    0.27
     overwhelm
    0.27
     niż
    0.26
     seemingly
    0.25
    ↵                ↵
    0.25
    åºŁçī©
    0.25
    æµĵæµĵçļĦ
    0.24
    çŀ¬
    0.24
    æĺ¾èijĹ
    0.24
    å¾Ĵ
    0.24
    Activations Density 0.005%

    No Known Activations