© 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. 107223
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ä¸į容
    -0.28
     stagger
    -0.27
    ikit
    -0.26
    yer
    -0.25
    ä»Ģä¹Īåľ°æĸ¹
    -0.25
    ple
    -0.24
    缼åħ¸
    -0.24
     complexity
    -0.24
    èľĤ
    -0.24
    ä¸įä»ħè¦ģ
    -0.23
    POSITIVE LOGITS
    ICES
    0.30
    ulos
    0.27
    TouchListener
    0.26
    ILD
    0.26
    强壮
    0.24
    è½½ä½ĵ
    0.24
    ä¼łæĿ¥
    0.24
     FullName
    0.24
    emade
    0.23
    å¨ģèĥģ
    0.23
    Activations Density 61.909%

    No Known Activations