© 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. 20-TRANSCODER-HP
    7. 141436
    Prev
    Next
    INDEX
    Explanations

    Length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aghan
    -0.29
    &_
    -0.29
     Britt
    -0.27
    \Context
    -0.26
    /**↵↵
    -0.25
    èĦ²
    -0.25
    åĮħ袱
    -0.23
     strtotime
    -0.23
    ç»ģ
    -0.23
    adeon
    -0.23
    POSITIVE LOGITS
    Del
    0.29
    æĺ¯éĿŀ
    0.26
    del
    0.25
    ENS
    0.25
     sworn
    0.25
    -del
    0.25
    OMET
    0.25
    Document
    0.25
    人为
    0.25
     probing
    0.24
    Activations Density 3.128%

    No Known Activations