© 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. 108134
    Prev
    Next
    INDEX
    Explanations

    Text containing "Inv" or French

    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
     temper
    -0.28
    èİ·æĤī
    -0.28
    á»ģn
    -0.26
     segue
    -0.26
    -0.25
     option
    -0.25
     unfortunately
    -0.24
    .Qt
    -0.24
    dong
    -0.24
    ser
    -0.24
    POSITIVE LOGITS
    è·¯è¿ĩ
    0.25
    .raise
    0.24
     Died
    0.24
    åħ¥å¸Ĥ
    0.24
    riz
    0.24
    滥
    0.23
    çĹķ
    0.23
     Euros
    0.22
    lected
    0.22
    æ°ĽåĽ´
    0.22
    Activations Density 0.366%

    No Known Activations