© 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. 33-TRANSCODER-HP
    7. 53859
    Prev
    Next
    INDEX
    Explanations

    business and market analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     portfolio
    -0.26
    acula
    -0.25
    tı
    -0.25
    utex
    -0.25
    æĤłæĤł
    -0.24
    è¡Ķæİ¥
    -0.24
    èĬ
    -0.23
    ylum
    -0.23
    atile
    -0.23
     immun
    -0.23
    POSITIVE LOGITS
     Rewards
    0.30
    letter
    0.30
     Letter
    0.30
     Companies
    0.27
     Insight
    0.27
    龸éģĵ
    0.26
     Insights
    0.26
     Surveillance
    0.26
    Letter
    0.25
    åħ¬åı¸çļĦ
    0.25
    Activations Density 0.035%

    No Known Activations