© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17942
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    Negative Logits
     present
    -0.27
    abis
    -0.26
    ENU
    -0.24
    ORA
    -0.24
    ystem
    -0.24
    çĩĶ
    -0.24
    çİ°
    -0.24
    èĸ°
    -0.24
     converters
    -0.24
    quals
    -0.23
    POSITIVE LOGITS
    åĮĢ
    0.36
    raz
    0.29
    åĪĨ
    0.28
    éĹŃ
    0.27
    æļĹ
    0.27
    ÑĢÑı
    0.27
    å¹´ä¹ĭä¹ħ
    0.27
    çĽı
    0.26
    è£ľ
    0.26
    æ·±
    0.25
    Activations Density 1.387%

    No Known Activations