© 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. 108367
    Prev
    Next
    INDEX
    Explanations

    fact

    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
    çļĦè¿ĽæŃ¥
    -0.26
    iliate
    -0.25
    èĩªä¸»
    -0.25
    arer
    -0.24
    urance
    -0.24
    å±ŀäºİèĩªå·±
    -0.23
    imu
    -0.23
    åĽºçĦ¶
    -0.23
    .fixed
    -0.23
     autonomous
    -0.23
    POSITIVE LOGITS
     sil
    0.33
    å¡«è¡¥
    0.27
    sil
    0.27
    pun
    0.26
     Played
    0.26
     Sil
    0.26
    被è¯Ħ为
    0.25
     phê
    0.25
    Sil
    0.24
    æİĴè¡Į
    0.24
    Activations Density 3.783%

    No Known Activations