© 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. 31-TRANSCODER-HP
    7. 19225
    Prev
    Next
    INDEX
    Explanations

    to or from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĢ示
    -0.33
    ä¸Ģéģĵ
    -0.27
    æīĢè¿°
    -0.26
    ä¸Ģ头
    -0.26
    å¼Ł
    -0.25
    unner
    -0.25
    åħĭæĸ¯
    -0.25
    硬度
    -0.24
    ãĢģ
    -0.24
    acre
    -0.24
    POSITIVE LOGITS
     fully
    0.35
     complete
    0.32
     the
    0.32
     collecting
    0.32
     integrating
    0.31
     something
    0.31
     completely
    0.31
     full
    0.31
     hands
    0.31
     entire
    0.30
    Activations Density 1.233%

    No Known Activations