© 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. 63932
    Prev
    Next
    INDEX
    Explanations

    Opinions and justifications

    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
    off
    -0.28
    ãĥ©ãĤ¤ãĥ³
    -0.26
    -off
    -0.26
    Ham
    -0.25
    intel
    -0.25
     Manual
    -0.25
    æ°ĵ
    -0.25
    Off
    -0.25
    ä»Ģä¹Īåij¢
    -0.24
    offline
    -0.24
    POSITIVE LOGITS
    æµĭ
    0.28
    asto
    0.28
    æĪIJå°±æĦŁ
    0.26
    ế
    0.25
    å£°éŁ³
    0.24
     pound
    0.23
    Driver
    0.23
     Dien
    0.23
     nip
    0.23
    stadt
    0.23
    Activations Density 13.862%

    No Known Activations