© 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. 14-TRANSCODER-HP
    7. 39410
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éŀħ
    -0.28
    uur
    -0.27
    æ´»ä¸ĭåİ»
    -0.26
    zl
    -0.25
    没åħ³ç³»
    -0.25
    çī©ä»·
    -0.25
    ordo
    -0.24
     Carla
    -0.24
    æ¯ĶåĪĨ
    -0.24
    otle
    -0.24
    POSITIVE LOGITS
    ế
    0.26
     embr
    0.25
    åħĪ
    0.25
    isode
    0.25
    uyá»ģn
    0.24
    樱
    0.24
    åºĶ注æĦı
    0.24
    Ế
    0.24
    _roll
    0.23
    rug
    0.23
    Activations Density 0.916%

    No Known Activations