© 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. 141572
    Prev
    Next
    INDEX
    Explanations

    because

    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
    /MIT
    -0.28
    implementation
    -0.27
    è¿Ń代
    -0.26
    åĬ¡å¿ħ
    -0.26
    iones
    -0.25
    orra
    -0.25
    wei
    -0.25
    å·Ŀ
    -0.24
    裸
    -0.24
    anni
    -0.24
    POSITIVE LOGITS
    ylum
    0.27
    ucas
    0.27
     traps
    0.27
    еÑĩа
    0.26
    éĢĤåIJĪèĩªå·±
    0.26
    ott
    0.25
    cestor
    0.25
    Emer
    0.25
    ERS
    0.24
    åĭĥ
    0.24
    Activations Density 24.371%

    No Known Activations