© 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. 95057
    Prev
    Next
    INDEX
    Explanations

    life

    np_max-act-logits · gemini-2.0-flash
    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
    vard
    -0.32
     Vox
    -0.28
    stack
    -0.28
    bro
    -0.27
    wh
    -0.27
    stadt
    -0.27
    spaces
    -0.27
    broker
    -0.27
    AXB
    -0.26
    .smtp
    -0.26
    POSITIVE LOGITS
    ç²ĺ
    0.28
    вл
    0.28
    BOUND
    0.28
    -io
    0.25
    ¢åįķ
    0.25
    çĽIJåŁİ
    0.24
    iens
    0.24
    adden
    0.24
    iente
    0.23
    RIES
    0.23
    Activations Density 0.002%

    No Known Activations