© 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. 58282
    Prev
    Next
    INDEX
    Explanations

    Spanish texts

    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
    olver
    -0.31
     desc
    -0.28
    wd
    -0.27
    人大
    -0.25
    æĸ¯åŁº
    -0.24
    人
    -0.24
     Sparks
    -0.24
     Application
    -0.24
    ector
    -0.24
    wdx
    -0.24
    POSITIVE LOGITS
     Dread
    0.26
     squeeze
    0.26
    eus
    0.26
    nature
    0.26
    åĬ³åĬ¡æ´¾éģ£
    0.26
    ÑīениÑı
    0.25
    bsolute
    0.25
     suggestive
    0.25
    .execution
    0.24
     entrusted
    0.24
    Activations Density 0.012%

    No Known Activations