© 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. 22-TRANSCODER-HP
    7. 111396
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desc
    -0.33
    desc
    -0.29
    ossa
    -0.25
    uml
    -0.25
    ï¼īãĢģ
    -0.25
    -desc
    -0.25
    Descending
    -0.24
    APT
    -0.23
     Scotia
    -0.23
    oshi
    -0.23
    POSITIVE LOGITS
    eted
    0.28
    rike
    0.27
     how
    0.25
     (\
    0.24
    åľ°å¤Ħ
    0.23
    eter
    0.23
    åıĺæĽ´
    0.23
    etes
    0.23
    åħħå®ŀ
    0.22
    çļĭ
    0.22
    Activations Density 0.029%

    No Known Activations