© 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. 18-TRANSCODER-HP
    7. 89627
    Prev
    Next
    INDEX
    Explanations

    agreements, deals, negotiations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ²
    -0.30
    CurrentValue
    -0.29
    åĭģ
    -0.28
    é¡¹çĽ®çļĦ
    -0.27
    iola
    -0.27
    edin
    -0.26
    è¿Ļç¯ĩ
    -0.26
    çİ°çĬ¶
    -0.26
    ÙĨÙĬ
    -0.26
    asn
    -0.25
    POSITIVE LOGITS
    å°ĺ
    0.28
    herits
    0.27
     [|
    0.27
    AIM
    0.25
     busiest
    0.24
    ÑĢÑĥд
    0.24
    å¸Ń
    0.23
    sheets
    0.23
    outes
    0.23
    atics
    0.23
    Activations Density 15.955%

    No Known Activations