© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 112417
    Prev
    Next
    INDEX
    Explanations

    Military troops/forces

    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
    hä
    -0.26
    大æ°Ķ
    -0.25
    atee
    -0.25
     Bout
    -0.24
    rnd
    -0.24
    -done
    -0.24
     Ribbon
    -0.24
     determin
    -0.24
    ppe
    -0.23
    飽
    -0.23
    POSITIVE LOGITS
    们
    0.32
    ng
    0.28
    æĸ¯åĿ¦
    0.27
    们çļĦ
    0.27
     civil
    0.27
     ra
    0.27
    ships
    0.26
    line
    0.26
    å®Ī
    0.26
     hosting
    0.26
    Activations Density 0.070%

    No Known Activations