© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108098
    Prev
    Next
    INDEX
    Explanations

    computer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rays
    -0.28
    toc
    -0.26
    çĪ±ç¾İ
    -0.26
    è¿
    -0.25
    ejs
    -0.24
     dagger
    -0.23
    ilde
    -0.23
    ÑĩÑĥ
    -0.23
    itor
    -0.23
    Official
    -0.23
    POSITIVE LOGITS
    æĪ¿
    0.34
    &action
    0.29
    å°ı游æĪı
    0.28
     science
    0.28
    ç§ijåѦ
    0.28
     sci
    0.27
     surround
    0.27
    çĽİ
    0.26
     nl
    0.26
     vision
    0.25
    Activations Density 1.903%

    No Known Activations