© 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. 9-TRANSCODER-HP
    7. 29382
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    event
    -0.28
    okes
    -0.27
    naires
    -0.26
    缨
    -0.26
    äºĭ件
    -0.25
    NER
    -0.25
     ferr
    -0.25
    osti
    -0.25
    碣
    -0.24
    esz
    -0.24
    POSITIVE LOGITS
     bags
    0.31
    æ´ŀ
    0.28
    绶
    0.28
    warm
    0.27
    åĽŀåĪ°å®¶
    0.26
    _bag
    0.26
     warmed
    0.25
     warmer
    0.25
    oup
    0.25
    ìĬ¬
    0.25
    Activations Density 0.419%

    No Known Activations