© 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. 141294
    Prev
    Next
    INDEX
    Explanations

    source code

    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
     trans
    -0.26
    æĦį
    -0.25
    é«ij
    -0.25
    Palindrome
    -0.25
     snapped
    -0.24
    WithValue
    -0.24
    üler
    -0.24
    .hy
    -0.23
     Gaul
    -0.23
    ES
    -0.23
    POSITIVE LOGITS
    ozo
    0.27
     sürü
    0.25
    å°±è¦ģ
    0.24
    .CG
    0.24
     scre
    0.23
    kHz
    0.23
    /internal
    0.23
     surely
    0.23
    .EventQueue
    0.23
     banc
    0.22
    Activations Density 1.420%

    No Known Activations