© 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. 63802
    Prev
    Next
    INDEX
    Explanations

    Geographic locations

    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
    ighth
    -0.31
    ä¸Ķ
    -0.27
    rew
    -0.25
    ign
    -0.25
    便åĪ©
    -0.24
    对æīĭ
    -0.24
    privileged
    -0.24
    åĪ°äºĨ
    -0.24
    пи
    -0.24
    ect
    -0.24
    POSITIVE LOGITS
    ì¸ł
    0.29
     Economist
    0.25
    configured
    0.25
     getConfig
    0.24
    åı£è¯Ń
    0.23
    è½°
    0.23
    缤纷
    0.23
    getConfig
    0.23
     Conflict
    0.23
     Folk
    0.23
    Activations Density 3.853%

    No Known Activations