© 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. 25-TRANSCODER-HP
    7. 107053
    Prev
    Next
    INDEX
    Explanations

    business

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åı¯èĥ½
    -0.28
    æĢ¥æĢ§
    -0.27
    DN
    -0.27
    æ¾Ħæ¸ħ
    -0.26
    inition
    -0.25
    ä¹ī
    -0.24
    æĤ£
    -0.24
    ãĥ³ãĥĪ
    -0.24
    rika
    -0.24
     PLA
    -0.24
    POSITIVE LOGITS
    ffd
    0.28
     knowledgeable
    0.27
    ä¸Ģ对
    0.26
    UEL
    0.25
    lah
    0.25
     Kil
    0.25
     mineral
    0.25
     accounting
    0.25
     Kun
    0.25
    ofs
    0.25
    Activations Density 1.005%

    No Known Activations