© 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. 19601
    Prev
    Next
    INDEX
    Explanations

    non-English abbreviations

    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
     Metadata
    -0.36
     metadata
    -0.33
    metadata
    -0.32
    代谢
    -0.30
    Metadata
    -0.29
     refr
    -0.28
    etadata
    -0.28
    ãģķãĤī
    -0.28
    .metadata
    -0.28
    worthy
    -0.26
    POSITIVE LOGITS
    åij¼
    0.27
    åį¡
    0.27
    éĨĭ
    0.26
    Ar
    0.25
    ighbors
    0.25
     Po
    0.25
    ako
    0.25
     Ar
    0.24
    æ·ĺ
    0.24
    èĭı
    0.24
    Activations Density 17.936%

    No Known Activations